{ "complete": true, "report": { "bucket": "emo_Teasing", "label": "Intense Teasing", "definition": { "id": "emo_Teasing", "category": "emotion", "head": "emo_Teasing", "pole": "high", "label": "Intense Teasing", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_teasing/full-v2-sealed/sealed-selected", "mission": "emotion_teasing", "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": 6.336031436920166, "genuineness": 4.1010676288604735, "wer": 0.005485996076721883, "identity": 0.542112697660923, "voiceclap": 0.03619318103417754, "fitness": 0.7125191821648418, "steering_v2": 0.774482498806049, "raw_target": 0.932425429970026, "target_cdf": 0.774482498806049, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.356682405471802, "genuineness": 4.07919563293457, "wer": 0.005227150537634408, "identity": 0.542112697660923, "fitness": 0.753518820460545, "steering_v2": 0.8578112413079234 }, "none": { "n": 50, "ce": 6.31538046836853, "genuineness": 4.122939624786377, "wer": 0.005744841615809358, "identity": null, "fitness": 0.6715195438691386, "steering_v2": 0.6911537563041746 } } } } ], "selected_wording": { "id": "manual-c46a333eb8dd", "general": "Focus on a deliberate, exaggerated sweetness that hints at underlying, playful challenge.", "inline": [ "Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.", "Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.", "End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible." ], "cfg": 2.5, "recipe": "P09", "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": 2.5 }, "n": 20, "target_z": 2.1933593629692885, "target_raw": 1.5214930295944213, "ce": 6.196955251693725, "genuineness": 4.054844629764557, "identity": 0.5353847242891788, "wer": 0.013450292397660818, "valid_fraction": 1, "identity_delta": -0.00858442559838295, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 2.147460902922523, "target_raw": 1.4967990130186082, "ce": 6.191792511940003, "genuineness": 3.994594657421112, "identity": 0.5120176918804645, "wer": 0.022039473684210525, "valid_fraction": 0.95, "identity_delta": -0.03195145800709724, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": 2.1933593629692885, "target_raw": 1.5214930295944213, "ce": 6.196955251693725, "genuineness": 4.054844629764557, "identity": 0.5353847242891788, "wer": 0.013450292397660818, "valid_fraction": 1, "identity_delta": -0.00858442559838295, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": 2.095166009555549, "target_raw": 1.4686636254191399, "ce": 6.178687119483948, "genuineness": 4.127646720409393, "identity": 0.5420833542943001, "wer": 0.00625, "valid_fraction": 1, "identity_delta": -0.0018857955932617188, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": 1.2870605338597607, "target_raw": 1.0338915221393108, "ce": 6.224357485771179, "genuineness": 4.139571154117585, "identity": 0.5514373898506164, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": 0.007468239963054657, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": 1.2060790662655607, "target_raw": 0.9903223544359208, "ce": 6.239845705032349, "genuineness": 4.2064109444618225, "identity": 0.5294026657938957, "wer": 0.006666666666666666, "valid_fraction": 1, "identity_delta": -0.014566484093666076, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": 1.1663085763747096, "target_raw": 0.9689252719283103, "ce": 6.201323747634888, "genuineness": 4.223042440414429, "identity": 0.5336208045482635, "wer": 0.0029411764705882353, "valid_fraction": 1, "identity_delta": -0.010348345339298248, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 3.266796892396928, "target_raw": 2.099017506837845, "ce": 6.092509126663208, "genuineness": 3.954427921772003, "identity": 0.42248070538043975, "wer": 0.06612573099415205, "valid_fraction": 0.95, "identity_delta": -0.12148844450712204, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 3.04921876748348, "target_raw": 1.9819574177265167, "ce": 6.106408810615539, "genuineness": 3.940777575969696, "identity": 0.43539196699857713, "wer": 0.047526444788441695, "valid_fraction": 0.8, "identity_delta": -0.10857718288898469, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": 2.6242187619441597, "target_raw": 1.7533014416694641, "ce": 6.1810698986053465, "genuineness": 4.023464369773865, "identity": 0.4656680904328823, "wer": 0.008350533195734434, "valid_fraction": 1, "identity_delta": -0.0783010594546795, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 2.147460902922523, "target_raw": 1.4967990130186082, "ce": 6.191792511940003, "genuineness": 3.994594657421112, "identity": 0.5120176918804645, "wer": 0.022039473684210525, "valid_fraction": 0.95, "identity_delta": -0.03195145800709724, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": 2.128808554217428, "target_raw": 1.4867637872695922, "ce": 6.181069946289062, "genuineness": 4.016874587535858, "identity": 0.4963406309485435, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.04762851893901825, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": 1.9649414028528387, "target_raw": 1.3986009567975999, "ce": 6.2152234554290775, "genuineness": 4.0843420147895815, "identity": 0.5069651454687119, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.03700400441884995, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": 1.900195269353887, "target_raw": 1.3637666270136832, "ce": 6.18623263835907, "genuineness": 4.037585520744324, "identity": 0.5440909519791604, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": 0.00012180209159851074, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": 1.449829081498692, "target_raw": 1.1214632883667945, "ce": 6.182459878921509, "genuineness": 4.162792456150055, "identity": 0.521512845158577, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.022456304728984834, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": 1.3467773563216607, "target_raw": 1.0660200119018555, "ce": 6.214826273918152, "genuineness": 4.133608973026275, "identity": 0.5450785294175148, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0011093795299530029, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": 1.2392577842408106, "target_raw": 1.008172971010208, "ce": 6.178289985656738, "genuineness": 4.197938311100006, "identity": 0.5493291616439819, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": 0.005360011756420135, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": 1.2134277267692535, "target_raw": 0.9942760370671749, "ce": 6.193579626083374, "genuineness": 4.1615372657775875, "identity": 0.5565730899572372, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.012603940069675445, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": 1.123681597424792, "target_raw": 0.9459913581609726, "ce": 6.21482629776001, "genuineness": 4.223356318473816, "identity": 0.5459490448236466, "wer": 0.006666666666666666, "valid_fraction": 1, "identity_delta": 0.0019798949360847473, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": 0.9630126724141178, "target_raw": 0.859549218416214, "ce": 6.179481363296508, "genuineness": 4.26509199142456, "identity": 0.5266227267682553, "wer": 0.005718954248366013, "valid_fraction": 1, "identity_delta": -0.017346423119306564, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": 0.9609863169922642, "target_raw": 0.858459010720253, "ce": 6.243816995620728, "genuineness": 4.250970828533172, "identity": 0.544375678151846, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.00040652826428413393, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": 0.5520019657940317, "target_raw": 0.6384196817874909, "ce": 6.184644150733948, "genuineness": 4.16122350692749, "identity": 0.5263797342777252, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.017589415609836578, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 3.3406250325435076, "target_raw": 2.1387380838394163, "ce": 6.058951306343078, "genuineness": 3.929010009765625, "identity": 0.4481619944795966, "wer": 0.10254106467148263, "valid_fraction": 0.85, "identity_delta": -0.09580715540796518, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 3.230859398974871, "target_raw": 2.079682630300522, "ce": 6.090920567512512, "genuineness": 3.883508729934692, "identity": 0.42551752999424935, "wer": 0.06121388028895769, "valid_fraction": 0.95, "identity_delta": -0.11845161989331246, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 3.102343752942764, "target_raw": 2.0105394065380096, "ce": 6.103628849983215, "genuineness": 3.9534865498542784, "identity": 0.4721872374415398, "wer": 0.01200657894736842, "valid_fraction": 1, "identity_delta": -0.07178191244602203, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 2.9812499986151697, "target_raw": 1.9453892648220061, "ce": 6.116734266281128, "genuineness": 3.9858081579208373, "identity": 0.4888708494603634, "wer": 0.03849307705538355, "valid_fraction": 0.95, "identity_delta": -0.05509830042719841, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 2.925000049853884, "target_raw": 1.9151260018348695, "ce": 6.043264532089234, "genuineness": 3.8919813513755797, "identity": 0.4370079219341278, "wer": 0.08357714138286894, "valid_fraction": 0.9, "identity_delta": -0.10696122795343399, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 2.896093793102837, "target_raw": 1.8995740294456482, "ce": 6.134208130836487, "genuineness": 3.954898715019226, "identity": 0.4905391216278076, "wer": 0.015789473684210527, "valid_fraction": 0.9, "identity_delta": -0.05343002825975418, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 2.7964843927431358, "target_raw": 1.8459827721118927, "ce": 6.132619619369507, "genuineness": 4.046215033531189, "identity": 0.46412469893693925, "wer": 0.009375, "valid_fraction": 1, "identity_delta": -0.07984445095062256, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": 2.598828123528618, "target_raw": 1.7396409213542938, "ce": 6.13281819820404, "genuineness": 3.95693838596344, "identity": 0.4664840765297413, "wer": 0.017624269005847952, "valid_fraction": 1, "identity_delta": -0.07748507335782051, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 2.51308592715705, "target_raw": 1.6935104146599769, "ce": 6.164787435531617, "genuineness": 4.034761321544647, "identity": 0.4724237509071827, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.07154539898037911, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": 2.13945308406096, "target_raw": 1.4924906939268112, "ce": 6.179084229469299, "genuineness": 4.0669260263443, "identity": 0.4933448567986488, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.05062429308891296, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": 2.0201171887550022, "target_raw": 1.4282863050699235, "ce": 6.161610388755799, "genuineness": 4.046999537944794, "identity": 0.4688134461641312, "wer": 0.00625, "valid_fraction": 1, "identity_delta": -0.07515570372343064, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": 1.5015625024234527, "target_raw": 1.1492965959012509, "ce": 6.212244892120362, "genuineness": 4.180051648616791, "identity": 0.46164859384298323, "wer": 0.006458333333333333, "valid_fraction": 1, "identity_delta": -0.08232055604457855, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": -0.09626463820814948, "target_raw": 0.2896431379020214, "ce": 6.181467056274414, "genuineness": 4.325342011451721, "identity": 0.5439691498875618, "wer": 0.0027777777777777775, "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": -0.07185058752248132, "target_raw": 0.3027782402932644, "ce": 6.207677888870239, "genuineness": 4.38998510837555, "identity": 0.5553365230560303, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.011367373168468475, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": -0.2378173739787986, "target_raw": 0.2134857766330242, "ce": 6.157639026641846, "genuineness": 4.341032040119171, "identity": 0.5529488012194633, "wer": 0.008742690058479531, "valid_fraction": 1, "identity_delta": 0.00897965133190155, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": -0.2073486341919206, "target_raw": 0.22987838685512543, "ce": 6.196558141708374, "genuineness": 4.358605015277862, "identity": 0.5843567721545696, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": 0.04038762226700783, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": -0.3035058635922404, "target_raw": 0.17814444601535798, "ce": 6.261211471557617, "genuineness": 4.350320591926574, "identity": 0.5787997949123382, "wer": 0.016744588744588743, "valid_fraction": 0.98, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": 2.1701757692842025, "target_raw": 1.5090199303627014, "ce": 6.255175065994263, "genuineness": 4.159277949333191, "identity": 0.5305546429753304, "wer": 0.012233320455288419, "valid_fraction": 1, "identity_delta": -0.0482451519370079, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 2.0236718814567705, "target_raw": 1.4301987797021867, "ce": 6.257716703414917, "genuineness": 4.074551415443421, "identity": 0.5226720720529556, "wer": 0.02474120082815735, "valid_fraction": 0.98, "identity_delta": -0.05612772285938263, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 2.1701757692842025, "target_raw": 1.5090199303627014, "ce": 6.255175065994263, "genuineness": 4.159277949333191, "identity": 0.5305546429753304, "wer": 0.012233320455288419, "valid_fraction": 1, "identity_delta": -0.0482451519370079, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": -0.14650388782743207, "ci95_z": [ -0.3213476036567492, 0.08248047444944137 ], "language_deltas": { "en": -0.32734372524616195, "de": -0.15791018833911014, "fr": 0.29921876194415964, "nl": -0.3738280348994913, "es": -0.17265625259655654 }, "languages_improved": 1, "clear_gain": false, "delta_ce": 0.002541637420654297, "delta_genuineness": -0.08472653388977051, "delta_wer": 0.012507880372868931, "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": -0.14650388782743207, "ci95_z": [ -0.3213476036567492, 0.08248047444944137 ], "language_deltas": { "en": -0.32734372524616195, "de": -0.15791018833911014, "fr": 0.29921876194415964, "nl": -0.3738280348994913, "es": -0.17265625259655654 }, "languages_improved": 1, "clear_gain": false, "delta_ce": 0.002541637420654297, "delta_genuineness": -0.08472653388977051, "delta_wer": 0.012507880372868931, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 2.473681632876443, "ci95_z": [ 2.143457040575965, 2.8452734413515586 ], "language_deltas": { "en": 2.53320308267613, "de": 2.3073242528730793, "fr": 1.8976562221302942, "nl": 2.501611316299849, "es": 3.1286132904028614 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.006036405563354492, "delta_genuineness": -0.1910426425933838, "delta_wer": -0.004511268289300326, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 2.5, "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain" }, "reference_only": true, "updated": 1793024763.5654976, "example": { "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.", "sentences": [ "The road turns left behind the bridge.", "Keep going... until you reach the small wooden gate.", "I will meet you on the other side." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "language": "en", "seed": 1702, "scale": 0.0, "cfg": 2.5, "frames": 128, "reference": true } }, "rows": [ { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "002324ae1ed7954e383b119f4b797871063c7c5a72778491a48a632293735c28", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "20b3d55fb16c59c192ab1c3ec287baf1430780259673f4c45d5335788ded16ef", "generation_seconds_batch": 18.129441370954737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.134425550699234, "target_z": -0.38476562802931585, "ce": 6.125868320465088, "genuineness": 4.2751336097717285, "identity": 0.6714698076248169, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/002324ae1ed7954e383b119f4b797871063c7c5a72778491a48a632293735c28.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": "005527e7366a1ff995a00ae79a9319cb2b062f4397fc9640eaf09b32fc77e00d", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3b7737d0229717f60cf00f8ddac35e639eb5ae1ff2bd2a8743def9a17c2c6964", "generation_seconds_batch": 25.331630119937472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.38804030418396, "target_z": 1.9453124497999086, "ce": 6.268836498260498, "genuineness": 3.6789097785949707, "identity": 0.4675617814064026, "hypothesis": "I wrote the number on the envelope, wrote it carefully, and checked the last two digits. Call me when you have a moment.", "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_Teasing/005527e7366a1ff995a00ae79a9319cb2b062f4397fc9640eaf09b32fc77e00d.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "00ab0693e1ec5a02d2d137e80bbf43d1f5be27f5310d712de8b4f5f51be00cb3", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "64fcad477344dd84dcc8644679efc084fec6ba4deadcad56c3869ac094844d4e", "generation_seconds_batch": 16.603100317995995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5435600280761719, "target_z": 2.2343750173103762, "ce": 6.316492557525635, "genuineness": 4.074300289154053, "identity": 0.5852303504943848, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/00ab0693e1ec5a02d2d137e80bbf43d1f5be27f5310d712de8b4f5f51be00cb3.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "00ac56ff57befbea53f6d7b2470e7e854d6fd70a19fb4b79641b8732d2706d05", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "aa88d1a6e5318df2a10ec19ef44673b773f35872ca872b1f431324a455e7a78d", "generation_seconds_batch": 17.80272288096603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8668391704559326, "target_z": 0.976562415179156, "ce": 5.95112943649292, "genuineness": 3.8420867919921875, "identity": 0.5210089683532715, "hypothesis": "La puerta sigue abierta y he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/00ac56ff57befbea53f6d7b2470e7e854d6fd70a19fb4b79641b8732d2706d05.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": "00c649d2737657424a14cc0a83a2b26d3e8dc0ce8d09d68b6c078d56fd4e7ce8", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9e4484d528871905b2ec4131bc7ace2e1ebcdf66a69c88b4de19f22c3c0287fa", "generation_seconds_batch": 26.2553983660182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.013952374458313, "target_z": 1.2499998892135915, "ce": 6.284721851348877, "genuineness": 4.168440818786621, "identity": 0.4846959114074707, "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_Teasing/00c649d2737657424a14cc0a83a2b26d3e8dc0ce8d09d68b6c078d56fd4e7ce8.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "0169c771671b258dc5ce8c4e95ae9b9e16656c8b39bea998971aad5ce5bca2b4", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d25aa50d5a8d0bab2e37087ec84ab9b5f7d271105568e373a5b19772bcf13ba1", "generation_seconds_batch": 23.041949163074605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2749228477478027, "target_z": 3.5937499515309463, "ce": 5.95112943649292, "genuineness": 4.105680465698242, "identity": 0.5298029184341431, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0169c771671b258dc5ce8c4e95ae9b9e16656c8b39bea998971aad5ce5bca2b4.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "01a5a63d69da6e46ae3afa8b73d305cba4d1cd668e3be22123c4f0cac12baf7c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "25e582168842aa0ad0314a3a9610ac940d2276cb4f37ff6b11cef0d2eb54c6da", "generation_seconds_batch": 23.61997099907603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7285022735595703, "target_z": 2.578124858054914, "ce": 5.959072113037109, "genuineness": 3.785602569580078, "identity": 0.6788784861564636, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/01a5a63d69da6e46ae3afa8b73d305cba4d1cd668e3be22123c4f0cac12baf7c.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "f22f50fe409ec71d774973c060451b0341a2ea2b9fe7dafdd66a2fee02daf1cd", "generation_seconds_batch": 20.567554222070612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11866341531276703, "target_z": -0.4140625121172634, "ce": 6.0146708488464355, "genuineness": 4.645420074462891, "identity": 0.6806225776672363, "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_Teasing/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "024128d1e56071afbace36fca7b6f72d2496af80842ae600c36fb55eef33b823", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "30f49e69719e672746074c6458678d86fdeafc0bf120e09dabca58b57b57753a", "generation_seconds_batch": 23.091123237041757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9050382375717163, "target_z": 2.9062500484690537, "ce": 6.086154937744141, "genuineness": 3.7291181087493896, "identity": 0.23564457893371582, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/024128d1e56071afbace36fca7b6f72d2496af80842ae600c36fb55eef33b823.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "02d07d7614da8e9784e58f7cd0507244808be73f39aa44cc733c82f15a37656c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b0fb9f159a548c11e29156c768c5b905541ace8c18fded953656a2e9980a83ad", "generation_seconds_batch": 24.002939373953268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.031135320663452, "target_z": 3.140625121172634, "ce": 6.149696350097656, "genuineness": 3.9173994064331055, "identity": 0.6095902323722839, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/02d07d7614da8e9784e58f7cd0507244808be73f39aa44cc733c82f15a37656c.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "032de0ba874d16299642a0dfce1bbb8df3e138eb64ae432fae99d688f070d7a4", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0986f4fdc2cc8d3960162fff50adb5c2e8da9c8db31b48b1b94790a754a84ef1", "generation_seconds_batch": 23.32278904900886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3418047428131104, "target_z": 1.8593749896137741, "ce": 6.24500846862793, "genuineness": 3.8169827461242676, "identity": 0.46119433641433716, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/032de0ba874d16299642a0dfce1bbb8df3e138eb64ae432fae99d688f070d7a4.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "038a37badb650793aa097dacf85be95e0a9637889f88c0a700cef1563174a5cc", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "cfb15b2bad6d81e5e9bc67de052620e371311525478ea9b837bdd81af8e9e844", "generation_seconds_batch": 23.838571652886458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7701648473739624, "target_z": 0.7968750588552795, "ce": 6.181467056274414, "genuineness": 3.873466968536377, "identity": 0.6103149652481079, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/038a37badb650793aa097dacf85be95e0a9637889f88c0a700cef1563174a5cc.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "043c4c89f4faffd50788fb264fcea94792393142aff9126a5e2fc0f3d649e894", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b544c2da8a0f3576dc9840906ba67231df386d7dfa2969db534c245369681dac", "generation_seconds_batch": 22.46858184505254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5631555318832397, "target_z": 0.41210943082596363, "ce": 6.109982967376709, "genuineness": 4.281409740447998, "identity": 0.7475042343139648, "hypothesis": "J'ai trouvé la 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_Teasing/043c4c89f4faffd50788fb264fcea94792393142aff9126a5e2fc0f3d649e894.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "0508f1b74fa42d189f246c363a7338a56e59fc9333b063905e441d06d1b706d2", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "fbb4327c490ce5fa9e48b870c0601d0e5cbf927b1f67cfb5a986d99fa295ce98", "generation_seconds_batch": 17.96266670501791, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.127069890499115, "target_z": -0.39843750173103765, "ce": 6.197352409362793, "genuineness": 4.570107460021973, "identity": 0.7161831855773926, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0508f1b74fa42d189f246c363a7338a56e59fc9333b063905e441d06d1b706d2.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "0513fe733fc8541f753732ed07eb4731afeace680554de20f1e5124d7d2f896d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a635e74a83862828e0eef9d5ebb6d1ab04e3648185b7c332fea0c094bfa8c4c8", "generation_seconds_batch": 22.46858184505254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3586176633834839, "target_z": 1.8906249549930216, "ce": 6.340320587158203, "genuineness": 4.143336772918701, "identity": 0.4688072204589844, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0513fe733fc8541f753732ed07eb4731afeace680554de20f1e5124d7d2f896d.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "0542f1cfa06453b0788e70feaca956674c1af27361cfaab9399151c09c42a2b7", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "cd9c90a776c8a9f1016802da82b999cc1387bf440c880625b2f56549024322b3", "generation_seconds_batch": 23.135935576981865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3376015424728394, "target_z": 1.8515625536621665, "ce": 6.332377910614014, "genuineness": 4.268857479095459, "identity": 0.48232483863830566, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0542f1cfa06453b0788e70feaca956674c1af27361cfaab9399151c09c42a2b7.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "554052fc60a298d2bcb34672c073ad061290beacca6fb6e6046f38fc076c2701", "generation_seconds_batch": 17.23954866209533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.627254843711853, "target_z": 0.5312500207724515, "ce": 6.260893821716309, "genuineness": 4.507347106933594, "identity": 0.646511435508728, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann leg dich das Handy weg, sag mir, wann wir reden können,", "wer": 0.08333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.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": "05d48c993c37c4be7765f2f1a2fcda62edddc75c302f22425a03fa87e7ad18d0", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "59d76dfe5dc54e34e608ef827d200e242bfb1b9ab49ab6a9fba32f705e2060df", "generation_seconds_batch": 23.222850621910766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2829594612121582, "target_z": 1.75, "ce": 6.09409761428833, "genuineness": 4.262581825256348, "identity": 0.6328592896461487, "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_Teasing/05d48c993c37c4be7765f2f1a2fcda62edddc75c302f22425a03fa87e7ad18d0.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "0600f94f953cf28a338e3b9dcec945955ff8f4ceb257cbf82031c1c8810caeae", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "89cda98cfb17812473229e537ccb93db37286641ede1336fe65fc2703229e99c", "generation_seconds_batch": 16.871924870065413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1404194831848145, "target_z": 3.3437502284969676, "ce": 5.9431867599487305, "genuineness": 4.231201171875, "identity": 0.3976196050643921, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0600f94f953cf28a338e3b9dcec945955ff8f4ceb257cbf82031c1c8810caeae.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "065f53ab0f78b6637904cd08719c065b4b7f41e24154e5453bdee89ea8cb2e66", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6588c6f657205ff5f24a2d1aee9d7a2b55d320857688b16be316ef7e4f3d4a60", "generation_seconds_batch": 16.335963805089705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7575551271438599, "target_z": 0.7734375294276398, "ce": 5.9431867599487305, "genuineness": 4.024092197418213, "identity": 0.7392426133155823, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/065f53ab0f78b6637904cd08719c065b4b7f41e24154e5453bdee89ea8cb2e66.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": "069b6298dd9c8c089adae8f74c501d2add168be45125ee446ffc3643c30a677d", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "214a0e2113a70c68c5eb3b7f19ab73a05e9addc285291034277efa267797290d", "generation_seconds_batch": 23.38063573196996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5939987897872925, "target_z": 2.3281249134481183, "ce": 6.459460258483887, "genuineness": 4.111956596374512, "identity": 0.2633029818534851, "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_Teasing/069b6298dd9c8c089adae8f74c501d2add168be45125ee446ffc3643c30a677d.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "0714ab423191e99f5a45116db49849b9cc6654862561e790cec065a55c04d1a6", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1170e33a9cbdebe67c9163939b162813e5eff50f32e7f18e6c2bcff3d70bcc11", "generation_seconds_batch": 24.56082910404075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6111817359924316, "target_z": 4.218750145407161, "ce": 5.8875885009765625, "genuineness": 3.5220088958740234, "identity": 0.31260770559310913, "hypothesis": "La puerta sigue abierta. He dejado tu abrijo sobre la silla. Dime cuándo estás lista.", "wer": 0.13333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0714ab423191e99f5a45116db49849b9cc6654862561e790cec065a55c04d1a6.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "076bb873307d971b31d805e160c7da2cfdd451722f65c0d547e87cbc025580b9", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c5d66d458c741a366ba229f3ba51bc3c3744a5a135647f27a699be7b24fc9498", "generation_seconds_batch": 25.2451731209876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7533518671989441, "target_z": 0.7656249826896236, "ce": 6.419747352600098, "genuineness": 3.9927117824554443, "identity": 0.548865556716919, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/076bb873307d971b31d805e160c7da2cfdd451722f65c0d547e87cbc025580b9.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "07899023f0f57f64c710bfd23d626d4f9abadab91da93489634e1f0176485dd9", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3a65b84e4596906089b93d0e97b81df10ca458e20e08ddad56a2a09e5661294d", "generation_seconds_batch": 25.66390287701506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5852224826812744, "target_z": 0.45312499653792476, "ce": 6.24500846862793, "genuineness": 3.9927117824554443, "identity": 0.31349819898605347, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/07899023f0f57f64c710bfd23d626d4f9abadab91da93489634e1f0176485dd9.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "086850669a42fda208bee8a9da56eae0c3c4be0df46d9df8ef07401a7bcf189c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "58247fe043807e194e46ffdb79395ec449e98c453c3e3b2bc8e4e91471ab10ec", "generation_seconds_batch": 24.022367710014805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.705014705657959, "target_z": 0.6757813045276854, "ce": 6.205295085906982, "genuineness": 4.137060642242432, "identity": 0.6768759489059448, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/086850669a42fda208bee8a9da56eae0c3c4be0df46d9df8ef07401a7bcf189c.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "08786d0200ada2f856049f00e3d2011a46836c7f3843eb0be729f826f15146d1", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "fe297291a2e7bdc6bc4420a7dbdddaeba6276bf852e81cfc22f565cbb7c9ddad", "generation_seconds_batch": 24.5974917790154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.375800609588623, "target_z": 3.781250186952064, "ce": 5.903473377227783, "genuineness": 3.8797430992126465, "identity": 0.15700748562812805, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/08786d0200ada2f856049f00e3d2011a46836c7f3843eb0be729f826f15146d1.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "08dc8f8bf2bad6b3651d2ae1873adf38abcc9afe982f0897ef9d0e71ea11e524", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3c5bab82e2a8b4d51e5fcbdfc9127e6cddb9228b5f08db6af64bb1737b2da5dc", "generation_seconds_batch": 28.005812659976073, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36665427684783936, "target_z": 0.046875003462075265, "ce": 6.348263263702393, "genuineness": 4.413206577301025, "identity": 0.6733521223068237, "hypothesis": "J'ai trouvé la 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_Teasing/08dc8f8bf2bad6b3651d2ae1873adf38abcc9afe982f0897ef9d0e71ea11e524.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "08e263d986be8066e9b609a1638106eb32348e96a8c6a726bcce409ee4d63b62", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "66428e0b6c53d05b61411ec16de6131b4c305aab9e8ec9d93ee42118585f90f4", "generation_seconds_batch": 17.223058811970986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8125669956207275, "target_z": 2.7343749065239678, "ce": 6.252951145172119, "genuineness": 4.105680465698242, "identity": 0.5004953742027283, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/08e263d986be8066e9b609a1638106eb32348e96a8c6a726bcce409ee4d63b62.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": "08f60103fb3f4f3cfd2050b07a95e2c97825b1efa61d362f71086deac3c15f9c", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fc4777ee0ad354cb0efac957110f5635d8fffbb10a376b8c2d67b2e9e752413c", "generation_seconds_batch": 19.03884321206715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1820818185806274, "target_z": 1.562499986151699, "ce": 6.3641486167907715, "genuineness": 4.068024158477783, "identity": 0.381478488445282, "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_Teasing/08f60103fb3f4f3cfd2050b07a95e2c97825b1efa61d362f71086deac3c15f9c.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "09a1c3d55a670d1b8a171c2c26fe6d3b96f4da9fab17183c5f115093a745abfc", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e1a1e933a8da1c07e0f4e3dcea6c1fd51a85e54ceb872edc98931eaa10130d90", "generation_seconds_batch": 19.25151489698328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1572322845458984, "target_z": 3.374999972303398, "ce": 6.340320587158203, "genuineness": 4.507347106933594, "identity": 0.6158668994903564, "hypothesis": "Ha ha! J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble what it contient.", "wer": 0.21052631578947367, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/09a1c3d55a670d1b8a171c2c26fe6d3b96f4da9fab17183c5f115093a745abfc.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "09e445ba1fb8bf4581b7cf0d69dee23f92feb97ef8806788984d2c5aa6d27226", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ae5a72984af288754b8e2e48aa3144175f336ea9c79d375e4e8e7937f75fbd73", "generation_seconds_batch": 27.162357995985076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8752456903457642, "target_z": 0.9921875086551881, "ce": 6.141753673553467, "genuineness": 4.20609712600708, "identity": 0.7848184108734131, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/09e445ba1fb8bf4581b7cf0d69dee23f92feb97ef8806788984d2c5aa6d27226.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "09fe3bdcadaf4fc2d4ed2c874758441eb28fed28021fc1778ce348272c7789ea", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1cc40a26c035a72126cab6e2614820388bcae22f8fdd889b37325b8111bb12ba", "generation_seconds_batch": 22.788364767911844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9635136127471924, "target_z": 1.1562499930758494, "ce": 6.109982967376709, "genuineness": 3.6914620399475098, "identity": 0.28305914998054504, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/09fe3bdcadaf4fc2d4ed2c874758441eb28fed28021fc1778ce348272c7789ea.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "0a8df9d799b4b5014913fd8f2f1301504f7f8e1edec75b4cbec072fc0cb53875", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "045735989d4c77a9c4d6a6dde6965447a79b78a85f5fd4a330a36ccbaa376db9", "generation_seconds_batch": 24.666635148925707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9467006921768188, "target_z": 1.1250000276966021, "ce": 6.221180438995361, "genuineness": 4.325342178344727, "identity": 0.5829738974571228, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0a8df9d799b4b5014913fd8f2f1301504f7f8e1edec75b4cbec072fc0cb53875.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "0aa22d62bf93167c25d0527d6a5e604ff54e715369aeece8fd5d5d979acb824e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8da539c04389ba17162eb5ac4c94d96cea741b333cdea95ee2bf7683055fcf04", "generation_seconds_batch": 24.027742718928494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.073167562484741, "target_z": 3.218749923834344, "ce": 5.927301406860352, "genuineness": 3.9927117824554443, "identity": 0.5867588520050049, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0aa22d62bf93167c25d0527d6a5e604ff54e715369aeece8fd5d5d979acb824e.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "0bf6ef9389bd29d505a10ef1106fdae42a25a147d33f32333f932ba8a3f3c5f0", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "fd0e51ea10abbce0b3b9b771878d32db03845ab2128d1a1ac5af4a03d4d6c37a", "generation_seconds_batch": 26.61520223901607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8966317176818848, "target_z": 2.8906249549930214, "ce": 5.982900142669678, "genuineness": 3.625563621520996, "identity": 0.5189336538314819, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0bf6ef9389bd29d505a10ef1106fdae42a25a147d33f32333f932ba8a3f3c5f0.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "0c4e9a0106e6852e055796ab1f7d0c26ca274a5be7dcbd11eee1734d08e44e04", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3ebc4a03d5dc7c1c4a8c4231b340f799def7ae0859859dd6b239826c3d7c5d69", "generation_seconds_batch": 23.819836228969507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1320128440856934, "target_z": 3.3281249134481183, "ce": 6.1020402908325195, "genuineness": 4.111956596374512, "identity": 0.6422376036643982, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0c4e9a0106e6852e055796ab1f7d0c26ca274a5be7dcbd11eee1734d08e44e04.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "77265e58e92c9ea820ef21a6805173b582f3dd0fa8b392b7d0a9c6af4b993296", "generation_seconds_batch": 18.123831278993748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06191974878311157, "target_z": -0.5195312560586317, "ce": 6.24500846862793, "genuineness": 4.419482707977295, "identity": 0.6628420352935791, "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_Teasing/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "0cc1876b21cfce2c10aa4701de857f5fe039b38b7bbdcb791d718de322378c9f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2792c5166af8992b4b671c42a38160b6c0138e8016660ce9e4e852772b50a83e", "generation_seconds_batch": 24.471357174101286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.451088786125183, "target_z": 2.0624998753652903, "ce": 5.8875885009765625, "genuineness": 3.8922953605651855, "identity": 0.6653845906257629, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0cc1876b21cfce2c10aa4701de857f5fe039b38b7bbdcb791d718de322378c9f.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "0cd32cc070683bf1b26094c264567aec9e351cfb0288665fac70083b2cdfcd45", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e19927d15cbf420cb318637baae1d9dd03d67faef7688763f46af24007c1d875", "generation_seconds_batch": 15.692940325010568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6251531839370728, "target_z": 0.5273436920102393, "ce": 6.229123115539551, "genuineness": 4.243753433227539, "identity": 0.6978139281272888, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0cd32cc070683bf1b26094c264567aec9e351cfb0288665fac70083b2cdfcd45.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "0cec17718a18cd4eb8f610fabcc107d4d644855b52ecad360b50d738274c8f16", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "18f815b92340693a3a66730fe5abd95878cc51f48b831eafea8654861f0c34b2", "generation_seconds_batch": 25.098366640973836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0854073762893677, "target_z": 1.3828124082550055, "ce": 6.4912309646606445, "genuineness": 4.281409740447998, "identity": 0.6840870976448059, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0cec17718a18cd4eb8f610fabcc107d4d644855b52ecad360b50d738274c8f16.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "0cf9844b460154ebfb8ce7eacf4be670367c67ed32780de93f6119759c92440d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "428bbaf64345aac515ce65a168cdc2c7c165e0d687c2dc8a3b5df08ff5185ace", "generation_seconds_batch": 33.10968038300052, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3333982229232788, "target_z": 1.843749896137742, "ce": 6.252951145172119, "genuineness": 4.243753433227539, "identity": 0.2431686967611313, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0cf9844b460154ebfb8ce7eacf4be670367c67ed32780de93f6119759c92440d.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "0d2575b86297c78a2b51b485b5fe7e52d68b94f714ac505b985f981ab0c169d3", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1f2f70b4d2619afe4183810260ca4a982e4c3bc97551c1e5950872af4935c4e8", "generation_seconds_batch": 22.963030923972838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8465628623962402, "target_z": 4.656250103862258, "ce": 6.316492557525635, "genuineness": 4.18726921081543, "identity": 0.31958407163619995, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0d2575b86297c78a2b51b485b5fe7e52d68b94f714ac505b985f981ab0c169d3.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "0d8060fc43ca015b19fa632d7f38f63e76603fe32085541615aef1844ae0c884", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e47e4069c4bb960796341ba1e3781bc33c03c4210d681c407c2bc26820ad3b90", "generation_seconds_batch": 16.6727786839474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4048532247543335, "target_z": 1.976562415179156, "ce": 6.332377910614014, "genuineness": 3.936227321624756, "identity": 0.3897150754928589, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0d8060fc43ca015b19fa632d7f38f63e76603fe32085541615aef1844ae0c884.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "0d89991d7dcad69a0dd42a5c56b36665fb4ba0309e94d62d8f1bc248d5dacb4c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5c0e6ffd7b0cd1330e6cda4c6242ad0203536a7f7cb399937dbf5cdb2e12b781", "generation_seconds_batch": 21.315445304033346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.228317379951477, "target_z": 1.6484374463378335, "ce": 6.062326908111572, "genuineness": 3.8044304847717285, "identity": 0.6676483154296875, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0d89991d7dcad69a0dd42a5c56b36665fb4ba0309e94d62d8f1bc248d5dacb4c.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": "0dd0ee5e5f7e62980c1decdc6d8910f24991688d5843cc3554c4e237d11db245", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c9d9cf5e295f9301663faa24adb590534ba42874599a267cfcf6a3f63db9b5dc", "generation_seconds_batch": 23.769933174015023, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1824517250061035, "target_z": 3.4218750311586774, "ce": 6.2767791748046875, "genuineness": 4.287685871124268, "identity": 0.5690767765045166, "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_Teasing/0dd0ee5e5f7e62980c1decdc6d8910f24991688d5843cc3554c4e237d11db245.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "0de0fad5beefaa1ebf139a742d6cc49f4d9577e1bc389bb3d327eee837c1f793", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8c3515b13b442adcd2a928c87a35d213089acca4de6149f3b8f580c3b322504b", "generation_seconds_batch": 25.85165354399942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4342758655548096, "target_z": 2.0312499099860433, "ce": 6.2767791748046875, "genuineness": 3.660081624984741, "identity": 0.3702085018157959, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0de0fad5beefaa1ebf139a742d6cc49f4d9577e1bc389bb3d327eee837c1f793.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "0e372c3716e62df1edfd4aa4fd305d053805d3be98228efc98d2d4a8b1b0214c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "961ebb222b8dae1203a622b777407854f21c44bac6f949664d2accc3f404348f", "generation_seconds_batch": 23.25451606407296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.039171814918518, "target_z": 1.296874948068871, "ce": 6.435632705688477, "genuineness": 4.444586753845215, "identity": 0.414247065782547, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0e372c3716e62df1edfd4aa4fd305d053805d3be98228efc98d2d4a8b1b0214c.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "0f3c43de8af22dab97da026feffb0fa262df8caaebbfd91387fd0cf195bff9cb", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8ed17fcff28ffe3a2262d6f6a23efdb1ce95e9e36221276e7b7191ae492a6b05", "generation_seconds_batch": 23.36133496905677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8878554105758667, "target_z": 1.015625038082828, "ce": 5.756534099578857, "genuineness": 3.7416701316833496, "identity": 0.3103446066379547, "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_Teasing/0f3c43de8af22dab97da026feffb0fa262df8caaebbfd91387fd0cf195bff9cb.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "0ff4d89fe00ecc224c3e90d85ae41cabae8d7bc850229c2d13bb6c3d2356a1e0", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6a5ca5cc1cb9047d80d190e62a7b0b2db9e81510b374b68bc0b2ef6ae7db1096", "generation_seconds_batch": 24.516981432097964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5351535081863403, "target_z": 2.218749923834344, "ce": 6.292664527893066, "genuineness": 4.231201171875, "identity": 0.7388252019882202, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/0ff4d89fe00ecc224c3e90d85ae41cabae8d7bc850229c2d13bb6c3d2356a1e0.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "10efaea6cf9fac31ef81828c86bfcdfd733384cecf59d16e6e617bed34faee6d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4dd4487e6a2be9a7ae51f95f25aeaf8102c88cb941e142c4d62258f6cf20bba0", "generation_seconds_batch": 23.607628048048355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4008055627346039, "target_z": 0.11035157180432727, "ce": 6.372091293334961, "genuineness": 4.093128204345703, "identity": 0.3722257614135742, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/10efaea6cf9fac31ef81828c86bfcdfd733384cecf59d16e6e617bed34faee6d.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "119812250601f02398b7edceaa6832035408825fd55a3cc42c08dfa8f54097a1", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c74f6048ea39a4bff45eeced7b4d83dd394cfd6d7c23d90e3e5c3b622dbe7698", "generation_seconds_batch": 17.928974578971975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2073012590408325, "target_z": 1.6093750450069784, "ce": 6.252951145172119, "genuineness": 4.193545341491699, "identity": 0.6542180776596069, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/119812250601f02398b7edceaa6832035408825fd55a3cc42c08dfa8f54097a1.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "11cd8db7bfe0481aa0b468cd3d3de2e4b55ef6723ea8936c6c773c185cb4b677", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1096056c4b8c540e1845a579b26cc21d22e9585882c8e7d52652362c3a19df44", "generation_seconds_batch": 23.909309884067625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.283329486846924, "target_z": 3.6093752665797956, "ce": 6.086154937744141, "genuineness": 3.8169827461242676, "identity": 0.40871721506118774, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/11cd8db7bfe0481aa0b468cd3d3de2e4b55ef6723ea8936c6c773c185cb4b677.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "121c96c83f460720e50a22d01496e14ef25a97f19923d92118259798e032f9b4", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "af746d6d83a3ccdec0aa4bfcb54b3af617de0463199beacc2524b23011fd9982", "generation_seconds_batch": 25.20699528499972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2997723817825317, "target_z": 1.7812499653792473, "ce": 6.260893821716309, "genuineness": 4.344170093536377, "identity": 0.6267600655555725, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/121c96c83f460720e50a22d01496e14ef25a97f19923d92118259798e032f9b4.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5b28ebb2eb551a510bfaf9155b4bcacc64bd255751d0b71b93c33604c02763fc", "generation_seconds_batch": 19.08152521797456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2599971890449524, "target_z": -0.1513671929094926, "ce": 6.23706579208374, "genuineness": 4.469690799713135, "identity": 0.7065035104751587, "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_Teasing/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "1317d8e1c2e934b4cbefb265993a027a01b202f9951bb132749ad6fe9dc07e57", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ca0dd9a42e748ecf3ce9657176a0fe81f76632c27536002c582debe3fbadaa76", "generation_seconds_batch": 16.711742885992862, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0223588943481445, "target_z": 1.2656249826896238, "ce": 6.070269584655762, "genuineness": 4.2249250411987305, "identity": 0.8253810405731201, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg, maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1317d8e1c2e934b4cbefb265993a027a01b202f9951bb132749ad6fe9dc07e57.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": "135e5845a8ccdd501eb6df5251d0d5face4ab0869fc7d89a2935037dde7e141e", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1016c60f3387f6a117b0148b33ad470f39f0e7329a7f0f390c68b5c44440125f", "generation_seconds_batch": 24.036257885047235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8773473501205444, "target_z": 0.9960938374174004, "ce": 6.419747352600098, "genuineness": 3.998987913131714, "identity": 0.32072383165359497, "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_Teasing/135e5845a8ccdd501eb6df5251d0d5face4ab0869fc7d89a2935037dde7e141e.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "13989ec5ed337a5330054a8b534e4b0a47a9cc967d661299cb44ebdbf2e6ea5e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f1d0821f082921f5b0f6b3aa693cfde8b1dfafe3a1bf7c05cd3e088b8cbef175", "generation_seconds_batch": 22.0687438279856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.417462944984436, "target_z": 1.9999999446067958, "ce": 6.165581703186035, "genuineness": 4.168440818786621, "identity": 0.6910184621810913, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/13989ec5ed337a5330054a8b534e4b0a47a9cc967d661299cb44ebdbf2e6ea5e.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "139a2a07b7d2e2f739746ff064ed74463ddf34ed8b99c434d9bc45fafd3eacff", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1e7f961092826bf089416c454810f387e77cc038d717020bae17181508fc0b00", "generation_seconds_batch": 24.04424065502826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4598653316497803, "target_z": 3.937500235421118, "ce": 5.998785495758057, "genuineness": 4.030367851257324, "identity": 0.4845157563686371, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.", "wer": 0.058823529411764705, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/139a2a07b7d2e2f739746ff064ed74463ddf34ed8b99c434d9bc45fafd3eacff.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "1425fe2ceca3a988bc3ba3b782ffa7cb8a2e606bcf7ecbc1d34f0fad5332a2f9", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b79091f3e51f87ba9c65cb29b37fe94d12a361932e7092ec62a3a175f8fb46f1", "generation_seconds_batch": 24.990077211055905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6608806848526001, "target_z": 0.5937499515309463, "ce": 6.213237762451172, "genuineness": 3.9425034523010254, "identity": 0.635637640953064, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1425fe2ceca3a988bc3ba3b782ffa7cb8a2e606bcf7ecbc1d34f0fad5332a2f9.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": "149df22aaf312fa34cf164d455e9b99e2645797b30fbaadc14626097d0c8d1c4", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "36d64eb54619b45008fdf120ea67e691a3b21503d92e3b52b20475599487e447", "generation_seconds_batch": 18.67624744796194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4850847721099854, "target_z": 3.9843752942763975, "ce": 6.308549880981445, "genuineness": 4.1998209953308105, "identity": 0.7309356927871704, "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_Teasing/149df22aaf312fa34cf164d455e9b99e2645797b30fbaadc14626097d0c8d1c4.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "14b9018061446a5987d94166b5b05c54017cf469261c32b2fab3228aa3c52be5", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4c153f3cbda590fee5afa37e31a65b8983f70f43fa68a18206b726fd78fc4123", "generation_seconds_batch": 17.28611433401238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.35898756980896, "target_z": 3.75, "ce": 6.078212261199951, "genuineness": 4.13078498840332, "identity": 0.591392993927002, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/14b9018061446a5987d94166b5b05c54017cf469261c32b2fab3228aa3c52be5.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "155583a820d082ec99e37bc141cbdca1e511fd385b9916573826f08668e7f4ac", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "832d41be934e4cddbf6500f504139f2d0132c52420a619b3bf7a3812dd52daf8", "generation_seconds_batch": 22.81505403597839, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5687793493270874, "target_z": 2.281249854592839, "ce": 6.078212261199951, "genuineness": 3.8044304847717285, "identity": 0.5089609622955322, "hypothesis": "He encontrado la cajita. Estaba junto en la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/155583a820d082ec99e37bc141cbdca1e511fd385b9916573826f08668e7f4ac.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "3954c80a4f78245fdae0372d6852aa57651a966c072c8c490ad50eb82eaa310a", "generation_seconds_batch": 19.706193636055104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11761261522769928, "target_z": -0.4160156211051653, "ce": 6.308549880981445, "genuineness": 4.356721878051758, "identity": 0.6887302994728088, "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_Teasing/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "161d8d3d288f543c1347cc22aaef5a354618a4de667e19a8b8caf7f7669ea479", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3ab8e8c7d75c0adf1970064fcdf514c9901edac6da537b5eda2f6ff98b63b8da", "generation_seconds_batch": 17.797230160911568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.190488338470459, "target_z": 1.578125079627731, "ce": 6.1020402908325195, "genuineness": 4.369274139404297, "identity": 0.6785074472427368, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/161d8d3d288f543c1347cc22aaef5a354618a4de667e19a8b8caf7f7669ea479.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "175e278e276e67f34f3300d334f417652e45bb19783bf792e99089e16353b8a4", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "17251226f85d1988604d17a59ed2ed412f415c91b57128d816f776f8f6475947", "generation_seconds_batch": 25.06631649506744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2615734040737152, "target_z": -0.14843750173103762, "ce": 5.998785495758057, "genuineness": 4.068024158477783, "identity": 0.3564283549785614, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/175e278e276e67f34f3300d334f417652e45bb19783bf792e99089e16353b8a4.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "17cc687563398f33ab7d958ff36446fc8c457e2af233f02fca0c15af49df8b11", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "85d69198059c5bb5df515a2cd96e58d47d56e26798e91d2268e61e92aafa40e4", "generation_seconds_batch": 16.871924870065413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2581100463867188, "target_z": 3.562500207724516, "ce": 5.911416053771973, "genuineness": 4.124508857727051, "identity": 0.6282472610473633, "hypothesis": "De deur staat nog open. Ik heb je Jals op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/17cc687563398f33ab7d958ff36446fc8c457e2af233f02fca0c15af49df8b11.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": "180296f6b5841d5d370b8d997616673697a73ec6ede22c1de7c5d0b96f1482ee", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "93a9232ee5e0438e87158bc55998361fd8866809c905f161bed45558c808cad5", "generation_seconds_batch": 17.465365809039213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2412970066070557, "target_z": 3.5312500207724518, "ce": 6.316492557525635, "genuineness": 3.886019229888916, "identity": 0.5229237675666809, "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_Teasing/180296f6b5841d5d370b8d997616673697a73ec6ede22c1de7c5d0b96f1482ee.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "188504eb6e9e809ce3d5cf4a6f634f98955882a5d2fa0f43c8806512edb894f5", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "face530ecbf885e7047f6e8186f7a0b16266cfe7919c77a168c6de455c20a45b", "generation_seconds_batch": 23.78086079796776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.325361728668213, "target_z": 3.6875000692415054, "ce": 6.173524379730225, "genuineness": 3.565941095352173, "identity": 0.40604647994041443, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/188504eb6e9e809ce3d5cf4a6f634f98955882a5d2fa0f43c8806512edb894f5.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "1891706a5a1ad2b418af4b97c49f9447e5aa656ab06561f2200e877cb2dbda1a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0253084a71b05ba7dabe2551caefbf6d8b3b4ebbdcd84233393f001aea9a0027", "generation_seconds_batch": 25.88108492398169, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2913659811019897, "target_z": 1.765625093476032, "ce": 6.419747352600098, "genuineness": 3.9927117824554443, "identity": 0.4122637212276459, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1891706a5a1ad2b418af4b97c49f9447e5aa656ab06561f2200e877cb2dbda1a.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "189e2a75786d79c80bca1ac284ce3e8e62eedbd974fe343ae104b59e079862ce", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f093e49e60411a92f7defd2445c6c66f0d4ae8261ce43ae547f594b25006cf06", "generation_seconds_batch": 20.912883772980422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.762128233909607, "target_z": 2.6406250103862257, "ce": 5.959072113037109, "genuineness": 4.243753433227539, "identity": 0.41183286905288696, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/189e2a75786d79c80bca1ac284ce3e8e62eedbd974fe343ae104b59e079862ce.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "18c8276f5ab112ffa71febdab92537cf8c909c6887478d48fcd7758e3818b3b5", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c767152d693c2882122c86fbad597198273a14a96fb1d2e929d9d3ef2887e6d6", "generation_seconds_batch": 24.756885462091304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.034968614578247, "target_z": 1.2890625121172634, "ce": 6.1894097328186035, "genuineness": 3.8922953605651855, "identity": 0.5883215665817261, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/18c8276f5ab112ffa71febdab92537cf8c909c6887478d48fcd7758e3818b3b5.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "18e6bf2d6a5cbeff15e8e9d06d54edbe18043332791068cb8617c73031f6117b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fac303c358aad2c911fa750e1d7d47c10ddd48c5d5f0cfeed70d6d3e5d03e1ae", "generation_seconds_batch": 22.734072212013416, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5519664287567139, "target_z": 2.2499998892135915, "ce": 6.2767791748046875, "genuineness": 4.375550270080566, "identity": 0.4726409912109375, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/18e6bf2d6a5cbeff15e8e9d06d54edbe18043332791068cb8617c73031f6117b.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "1946218ad0e4aa61d3acad6acc4772632391be6942d26666dcc7e922c7930fc1", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3502637d4751fc9f5eef9239e9ee013d7dbb2ae46b94ac8828d78ec57e267e5d", "generation_seconds_batch": 20.34164239000529, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8966317176818848, "target_z": 2.8906249549930214, "ce": 6.316492557525635, "genuineness": 4.381826400756836, "identity": 0.5154201984405518, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1946218ad0e4aa61d3acad6acc4772632391be6942d26666dcc7e922c7930fc1.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "1963c0181f28a77b60861e2e277e428ea6b0e2a9ba40a9b8bb44ed07d26d85e3", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "aef0cea2fdaa9c8ac7f8101ac47ccdebdc8cd81634ad4564317d32122b59322f", "generation_seconds_batch": 23.043383026029915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2749228477478027, "target_z": 3.5937499515309463, "ce": 5.990842819213867, "genuineness": 4.174716949462891, "identity": 0.6647891998291016, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1963c0181f28a77b60861e2e277e428ea6b0e2a9ba40a9b8bb44ed07d26d85e3.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": "19f6a3714460a1c9643a8226ea5768ca7eb4c87c8b7ca28a4f7174d04e52b980", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0c2a3f6c72d41f60bd1c81dafcfa2568b21582e404f322202bf132e20b278e8d", "generation_seconds_batch": 26.2553983660182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.602405309677124, "target_z": 2.3437500069241506, "ce": 6.324435234069824, "genuineness": 3.9550557136535645, "identity": 0.42562583088874817, "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_Teasing/19f6a3714460a1c9643a8226ea5768ca7eb4c87c8b7ca28a4f7174d04e52b980.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "1a281d740520501cf36ac82fda6c3130e8779a47cca8506da32dae0d003aa35c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "57c5d4f61b2401e74ab7f69abe9979b27523e4aae45ecb9a82ce51bfc4e341e0", "generation_seconds_batch": 27.078463296988048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.602405309677124, "target_z": 2.3437500069241506, "ce": 6.149696350097656, "genuineness": 4.074300289154053, "identity": 0.43972715735435486, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1a281d740520501cf36ac82fda6c3130e8779a47cca8506da32dae0d003aa35c.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "1b6fbe1d9c0ba42cc9b711e216c39c1f38235666a12a09522fa652f182ff26a1", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ecfdaf5488c83e58554f5ffdcd6db249a4f1114ee9f9c3db11bfd7d3ca7f6339", "generation_seconds_batch": 23.83314279804472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7449454069137573, "target_z": 0.75, "ce": 6.602428436279297, "genuineness": 4.432034492492676, "identity": 0.2775760591030121, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1b6fbe1d9c0ba42cc9b711e216c39c1f38235666a12a09522fa652f182ff26a1.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "1b8651c1619026cc6387ac9ae86b0b5a0f4262423c4dae7db2743456f66ad52e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f9e01796ce94bba5493083c9f5344a5db5e1891c2d30209172ac5b37549dbbc6", "generation_seconds_batch": 24.35890205996111, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.955476999282837, "target_z": 2.9999999446067958, "ce": 6.23706579208374, "genuineness": 3.848362922668457, "identity": 0.30826056003570557, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1b8651c1619026cc6387ac9ae86b0b5a0f4262423c4dae7db2743456f66ad52e.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "1ba64722695aab6ecfc2f788dc28836d6635602b12121099d063a1ee59d43960", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "903ddc82d4da807add1ca2d935afdb1904388db079e33de09b4f34cb00100c0b", "generation_seconds_batch": 24.671551696024835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9470704793930054, "target_z": 2.9843748511307635, "ce": 6.332377910614014, "genuineness": 4.419482707977295, "identity": 0.5097829103469849, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1ba64722695aab6ecfc2f788dc28836d6635602b12121099d063a1ee59d43960.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": "1bedc26c679c4b108e47c9e440949eea2a63bc52f63035a04dca7a8d22776f83", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d23ee795ed9000395aaae40c7ca6b21ff471e08d3d3a05e57c0dbd417dbbc209", "generation_seconds_batch": 19.745656339917332, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9803265333175659, "target_z": 1.187499958455097, "ce": 6.419747352600098, "genuineness": 4.024092197418213, "identity": 0.2446027398109436, "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_Teasing/1bedc26c679c4b108e47c9e440949eea2a63bc52f63035a04dca7a8d22776f83.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "1c0f379154b6a4f095c181e53f473096bded046f2bbb143c1b69e84ddfa0f265", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3614e8db13a6ecd9b8f609819ef77ef045caf0547c0baa3090278c995826d013", "generation_seconds_batch": 21.42496127996128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7873475551605225, "target_z": 2.6874998476686884, "ce": 6.252951145172119, "genuineness": 4.099404335021973, "identity": 0.5873220562934875, "hypothesis": "Ik 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_Teasing/1c0f379154b6a4f095c181e53f473096bded046f2bbb143c1b69e84ddfa0f265.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "1c405ca13e6ca1e839b67cbbdd9d0145c874937e2e2e5cc69eb5a0117c4089b2", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b59b7dd797b67cc5e755d8c15d339a88c940983e5e64e6522c67289a10d854fc", "generation_seconds_batch": 16.826161695062183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6111817359924316, "target_z": 4.218750145407161, "ce": 5.998785495758057, "genuineness": 4.030367851257324, "identity": 0.4073711037635803, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1c405ca13e6ca1e839b67cbbdd9d0145c874937e2e2e5cc69eb5a0117c4089b2.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "1c58b231675e8f106e4cfe24dec898ebbbcd769f6a1ccffc744ce841a77bf49a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8ad8b736c4784f2bf44ea4d3010bf77fe494798c36b03833e85d9da5c7a0b188", "generation_seconds_batch": 22.852830215007998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6948764324188232, "target_z": 2.5156249272964195, "ce": 6.205295085906982, "genuineness": 3.8169827461242676, "identity": 0.053078725934028625, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1c58b231675e8f106e4cfe24dec898ebbbcd769f6a1ccffc744ce841a77bf49a.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "1c7a690942254f601e7e29a5d8e0ed6e3cd5f48cf0bef2f84a895d12b29999f7", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "932e3ef6a6f51220ab74a5d02664513351841ad2edc58f94717260fa5aa0462e", "generation_seconds_batch": 20.912883772980422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4847147464752197, "target_z": 2.125000027696602, "ce": 6.141753673553467, "genuineness": 4.1998209953308105, "identity": 0.5124363303184509, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1c7a690942254f601e7e29a5d8e0ed6e3cd5f48cf0bef2f84a895d12b29999f7.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "1cb9f4bc8d05a7539d10a48c8354b928555cdedcb5d52f4aea7bb9e75a7257ae", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "513ba7dc7a1e55574d3c5d73f2aa35e67466ccb55559323c5bc83ab901af5b35", "generation_seconds_batch": 21.42496127996128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.770534634590149, "target_z": 2.656249882289441, "ce": 6.1020402908325195, "genuineness": 3.71028995513916, "identity": 0.05395710468292236, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1cb9f4bc8d05a7539d10a48c8354b928555cdedcb5d52f4aea7bb9e75a7257ae.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "1cbe513dcb32e2d7dfeb570591cd17e59415f4f8afceaf4e6c576192b42dacf4", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "affdb993c97aa38b0657fe5c39f80d9230c2a64d20d9d20395e59616b75ac28e", "generation_seconds_batch": 24.758166885003448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1320128440856934, "target_z": 3.3281249134481183, "ce": 6.0305562019348145, "genuineness": 4.118232727050781, "identity": 0.18223917484283447, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1cbe513dcb32e2d7dfeb570591cd17e59415f4f8afceaf4e6c576192b42dacf4.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "1d2995c6f666fc25ecfd011a4906cd1883286a0caf729a25f868df8adc29f1e9", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c974ef74dd03dc4a627008db227c2ce340d1b7aea2dfaaae61b769af77f0dd8c", "generation_seconds_batch": 23.611698842025362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6524742841720581, "target_z": 0.5781250796277311, "ce": 6.475345611572266, "genuineness": 4.093128204345703, "identity": 0.5879770517349243, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1d2995c6f666fc25ecfd011a4906cd1883286a0caf729a25f868df8adc29f1e9.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "fa0f09c67e4a342cd5db6a92855d49d42eada4bbbf1ade477ed06801405ffd99", "generation_seconds_batch": 20.047842141939327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11446018517017365, "target_z": -0.42187500346207524, "ce": 5.919358730316162, "genuineness": 4.319066047668457, "identity": 0.7046149969100952, "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_Teasing/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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "7e6747ae70746edca609b353a9bb0229bcad87348d88a7dcc71956e6229f5aa4", "generation_seconds_batch": 18.560719821951352, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11235857009887695, "target_z": -0.4257812491344812, "ce": 6.23706579208374, "genuineness": 4.532451152801514, "identity": 0.42880845069885254, "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_Teasing/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.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": "1d88a7a1c1b3d89d4a5f3df8d2819e53c4103ee0f7b61e540e89fe46391201f8", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7a9a69c4ba1a7769654e565804ead74d29e3cc34796bfb1bd3a94a44ea83d8bc", "generation_seconds_batch": 23.222850621910766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.795754075050354, "target_z": 2.7031249411447207, "ce": 6.23706579208374, "genuineness": 4.093128204345703, "identity": 0.6037564277648926, "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_Teasing/1d88a7a1c1b3d89d4a5f3df8d2819e53c4103ee0f7b61e540e89fe46391201f8.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "1dbb369852e90044baad577cdbd3bf84e005ea05fe1cef5268a7f9cd47b828fd", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cd43358ddc8ba36673ca0951dca05ccb374b42a1cdd68048eeb6fb0c2d800276", "generation_seconds_batch": 19.701561143039726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.073167562484741, "target_z": 3.218749923834344, "ce": 6.133810997009277, "genuineness": 4.017816066741943, "identity": 0.5644184350967407, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1dbb369852e90044baad577cdbd3bf84e005ea05fe1cef5268a7f9cd47b828fd.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "1e32058bd464a76cd2b0f2651346a51cacc456b470e4495aa178907201ebffef", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a009792882e097bab9d6799e42e56ef4630ea61d12c5f5bb6c9e0a98ffb1329f", "generation_seconds_batch": 23.46814400900621, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8465628623962402, "target_z": 4.656250103862258, "ce": 6.41180419921875, "genuineness": 4.457139015197754, "identity": 0.7579622864723206, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble what contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1e32058bd464a76cd2b0f2651346a51cacc456b470e4495aa178907201ebffef.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "1e4ccf8c8cb7ea6f4e6bdeeaa329853230866a46212bfb345ea2ac1d6805498a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8a1ee8c35156c82f5501d74d069be2cf4fbf3b1eaca68340d331b9716a760687", "generation_seconds_batch": 23.394666980020702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5463425517082214, "target_z": 0.38085935466030785, "ce": 6.181467056274414, "genuineness": 4.149612903594971, "identity": 0.6265283226966858, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1e4ccf8c8cb7ea6f4e6bdeeaa329853230866a46212bfb345ea2ac1d6805498a.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "3cda634a8d924a3d13476a3dc2823b588a074d4863cdaf3cf3b3df119d12fc19", "generation_seconds_batch": 20.047842141939327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10079967975616455, "target_z": -0.4472656141810148, "ce": 6.356205940246582, "genuineness": 4.055472373962402, "identity": 0.65901780128479, "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_Teasing/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.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": "1eb3eb02aebe26459fe216f948a40b040adaa7758e6e90b3e9edb6e043fcdb36", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "21422cb44fece610c1033f4b3542b3ae609d4ba3f6bc48cac5eb0ea3e408d6e5", "generation_seconds_batch": 24.036257885047235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6692872047424316, "target_z": 0.6093750450069785, "ce": 6.443574905395508, "genuineness": 3.9550557136535645, "identity": 0.49405810236930847, "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_Teasing/1eb3eb02aebe26459fe216f948a40b040adaa7758e6e90b3e9edb6e043fcdb36.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": "1edb598df3e28917eed2f90b445d8239b0a29c891645983cbcbff603cb90bf3b", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b887b8e33b793b9c60d10e29e36cf0def2d174c3af8f02a407239c66fa3afd39", "generation_seconds_batch": 17.622418954968452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.46543028950691223, "target_z": 0.2304687439413683, "ce": 6.24500846862793, "genuineness": 4.20609712600708, "identity": 0.7492040395736694, "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_Teasing/1edb598df3e28917eed2f90b445d8239b0a29c891645983cbcbff603cb90bf3b.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "1f072aff26e53e0fcf1837950b501c657785d52d7f039c8ae80e89f3b7123716", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3826dcbbcff3192476a6f7d3afcbab7bf8e9bb1260a09474e4baeeb002af8096", "generation_seconds_batch": 22.576886569033377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5183405876159668, "target_z": 2.187499958455097, "ce": 5.911416053771973, "genuineness": 3.660081624984741, "identity": 0.3954830765724182, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können.", "wer": 0.125, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1f072aff26e53e0fcf1837950b501c657785d52d7f039c8ae80e89f3b7123716.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "1f21f0ab68952bedc3807f8f69c51485e2e32bf446189dba4f3cb2d2fc26dd1b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5b65dfd1e36f98fe736c8d8f7a41fac87f2906e7246095a381395e9d4a9b0b56", "generation_seconds_batch": 22.476197196054272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9722899198532104, "target_z": 3.0312499099860433, "ce": 6.141753673553467, "genuineness": 4.250029563903809, "identity": 0.43972358107566833, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1f21f0ab68952bedc3807f8f69c51485e2e32bf446189dba4f3cb2d2fc26dd1b.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "1fa16dee1c91e7040111a523ff75dcbf54b19f9c8db38253b3dc6c4289ee46ef", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2c5cdae311f9c3baf252dbdf190e6c8a7c918d3c6bbf47868352b5ef8d0dd1af", "generation_seconds_batch": 23.819836228969507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.392613649368286, "target_z": 3.8125003739041285, "ce": 6.0305562019348145, "genuineness": 4.1998209953308105, "identity": 0.5565633773803711, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/1fa16dee1c91e7040111a523ff75dcbf54b19f9c8db38253b3dc6c4289ee46ef.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": "1fc7e305056ccb304ff032a4e03ed53637060ed09e41a0fc5f00c3479a1b234f", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7eb820eb610fb43925be5ce8177bb76e7c85e2637a8da1eb5304f17af9eb1aa6", "generation_seconds_batch": 17.631409064983018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9218511581420898, "target_z": 2.937500013848301, "ce": 6.419747352600098, "genuineness": 4.256305694580078, "identity": 0.43666329979896545, "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_Teasing/1fc7e305056ccb304ff032a4e03ed53637060ed09e41a0fc5f00c3479a1b234f.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": "1fe469ea3966459b20dbd16580975e314f69e77a551a7dd4eb38f23d185dccf7", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "10fa91633a16c8207ef586e2c8c1ed10c2e5ef1698923c8e4e4097e73cd56166", "generation_seconds_batch": 24.47488989494741, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2451303005218506, "target_z": 1.6796874117170808, "ce": 6.1020402908325195, "genuineness": 4.124508857727051, "identity": 0.7112420201301575, "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_Teasing/1fe469ea3966459b20dbd16580975e314f69e77a551a7dd4eb38f23d185dccf7.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "201b88895624de8758a027d4f6018ca5b980c501710136aac7948672cd54ff15", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "01b020ba64411bdb1fdc4b7af1a01f0691d476c5a86b6738f2a2f7e385f8ca7d", "generation_seconds_batch": 16.514878269983456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5673587322235107, "target_z": 0.41992186677757126, "ce": 6.109982967376709, "genuineness": 4.193545341491699, "identity": 0.6108692288398743, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/201b88895624de8758a027d4f6018ca5b980c501710136aac7948672cd54ff15.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "202330f375a4d430e52c46687aedc6107818480cf7346468ebab8f026a9a410a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6315189bf5adac0d71a0ca27216972bdb6ef8ffa123bae944bd14aafca79efd4", "generation_seconds_batch": 25.797876174096018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3712273836135864, "target_z": 1.9140624844206613, "ce": 6.197352409362793, "genuineness": 4.331617832183838, "identity": 0.4726024866104126, "hypothesis": "La puerta sigue ya rápida. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.13333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/202330f375a4d430e52c46687aedc6107818480cf7346468ebab8f026a9a410a.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "205ee20f4821be77a5daca95b1e03784ed28c5203ba436a59cbdaec6cffd9f3d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "de9398c4c6b712539e3e121671ff0cc53c7398e807bbf1a65991e286f0b8fb65", "generation_seconds_batch": 22.497601618990302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4342758655548096, "target_z": 2.0312499099860433, "ce": 6.157639026641846, "genuineness": 4.319066047668457, "identity": 0.8119183778762817, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/205ee20f4821be77a5daca95b1e03784ed28c5203ba436a59cbdaec6cffd9f3d.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "20a96e7dd49a32e5c12250dce511678371ab6d68a4f4bcaf8c4fdba9b012d339", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d49be2a24d94c20b4131dedc1de580716d6a0ad6b673f70048ffc99d71259502", "generation_seconds_batch": 24.73094028001651, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17225466668605804, "target_z": -0.31445312283620297, "ce": 6.435632705688477, "genuineness": 4.268857479095459, "identity": 0.20752829313278198, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/20a96e7dd49a32e5c12250dce511678371ab6d68a4f4bcaf8c4fdba9b012d339.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "2118eac21cdee38bc29a1725314f5a8d83d98541720cd9accf84332d78760d08", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f52c66286c1c7e76eb4cb9c19913b3fcff40be5e8bb82aea2b3c5bbf53feedef", "generation_seconds_batch": 25.270693861995824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4258694648742676, "target_z": 2.015625038082828, "ce": 6.157639026641846, "genuineness": 4.193545341491699, "identity": 0.7730021476745605, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2118eac21cdee38bc29a1725314f5a8d83d98541720cd9accf84332d78760d08.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "213c7b2d34dd28e2bc10fa9004c51573c7a0a1fbf511931ad2c6a439bca6ebfd", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2cde68ffb35f1f23b480b7dd16b0a924dd885d647da97e454d3c09373363c05d", "generation_seconds_batch": 23.1816362059908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2157076597213745, "target_z": 1.6249999169101936, "ce": 6.308549880981445, "genuineness": 4.344170093536377, "identity": 0.4685562551021576, "hypothesis": "I found little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/213c7b2d34dd28e2bc10fa9004c51573c7a0a1fbf511931ad2c6a439bca6ebfd.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "21a0c281f05b27bc71891b94292f22671b5141932980d26628b5af1df7d49ddd", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "78ca403e64081c620da8b73d645da97c06749da19ab87f48c2eb2fda2fc5b5df", "generation_seconds_batch": 22.39246042596642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9638835191726685, "target_z": 3.015625038082828, "ce": 6.308549880981445, "genuineness": 4.149612903594971, "identity": 0.1282242238521576, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/21a0c281f05b27bc71891b94292f22671b5141932980d26628b5af1df7d49ddd.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "21b685fe2d1bdafd796b5b5f81f711f59ef351e7b3d9e44276141648cfa7fc26", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c899f5a4bb1952f4a835f830970a3d6318427063de0ed4d6933b035e836d6dd7", "generation_seconds_batch": 24.671551696024835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.631458044052124, "target_z": 0.5390624567240592, "ce": 6.316492557525635, "genuineness": 4.394378662109375, "identity": 0.4485683739185333, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/21b685fe2d1bdafd796b5b5f81f711f59ef351e7b3d9e44276141648cfa7fc26.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "2214f25b26628506d7823da5b9bc2fe09de5424bbcd70840b6cc753c423356bd", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ac5f7eb02948fca402648ffeda06d668718f3421ffd4afa986dda9267268f8c6", "generation_seconds_batch": 17.880569062079303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.034968614578247, "target_z": 1.2890625121172634, "ce": 6.157639026641846, "genuineness": 4.469690799713135, "identity": 0.6790115833282471, "hypothesis": "J'ai trouvé la 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_Teasing/2214f25b26628506d7823da5b9bc2fe09de5424bbcd70840b6cc753c423356bd.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": "2216754e339fa1ad7e4b8a09ba10a1112d96a0386e10eb9acffd75a800ac9dd1", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8a1a1b64429f464028757832338a7050b7882fc5625557fd1e7b0eb479fedabe", "generation_seconds_batch": 17.144092753063887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8882251977920532, "target_z": 2.8749998615169896, "ce": 6.054384231567383, "genuineness": 4.005263805389404, "identity": 0.587638258934021, "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_Teasing/2216754e339fa1ad7e4b8a09ba10a1112d96a0386e10eb9acffd75a800ac9dd1.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "225fef47c01c6774550f473b44f1ba2b43b7a1cef68da8f6df3355526b1f9b67", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1226423ba2807c40f20b7eef5e1a6512e6a1d564120b55a3885cd6887273bcb5", "generation_seconds_batch": 25.772655499982648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7285022735595703, "target_z": 2.578124858054914, "ce": 6.268836498260498, "genuineness": 3.6977379322052, "identity": 0.30091947317123413, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/225fef47c01c6774550f473b44f1ba2b43b7a1cef68da8f6df3355526b1f9b67.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "23c15d8e26c4a77c5e0bb1a700c2e45dfb266040cb64fd12d3242ad7a7bba9cd", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "04047b5d60d9187265e2a188255a421b5e9c49693cf130a2f4b674d54939c66a", "generation_seconds_batch": 19.14694251003675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4931211471557617, "target_z": 2.140624899599817, "ce": 5.9431867599487305, "genuineness": 3.936227321624756, "identity": 0.36162030696868896, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/23c15d8e26c4a77c5e0bb1a700c2e45dfb266040cb64fd12d3242ad7a7bba9cd.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "23d211dae322c3b5d0561ef7abe411f01a7bb365210ad67414d498332af7cbea", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2c268f1afb93ea7544fe91fd38845f0094f59553b56e1ef551f049cc6c0c2c11", "generation_seconds_batch": 25.174343492952175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7701648473739624, "target_z": 0.7968750588552795, "ce": 6.157639026641846, "genuineness": 4.042920112609863, "identity": 0.6156152486801147, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/23d211dae322c3b5d0561ef7abe411f01a7bb365210ad67414d498332af7cbea.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "24343db51db44a6b2ec50f212825356d213487e0face2d2dacf48cf6b180414c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c1cf0bd3c0ed86f06f3d44ef43cfe475b35fc51291e78db56ebae43f6c0a1597", "generation_seconds_batch": 20.06594318698626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9470704793930054, "target_z": 2.9843748511307635, "ce": 5.855817794799805, "genuineness": 3.653805732727051, "identity": 0.5135566592216492, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/24343db51db44a6b2ec50f212825356d213487e0face2d2dacf48cf6b180414c.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "2464f9256695aad6a6d16a61c9b4dded133f83b6f9d4ba085a29e7189c7a00f1", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f058e83e3944158f6f844e2523c8f207c8dd96bc8bd8d7d6363b9ae18266f3c2", "generation_seconds_batch": 22.765621350961737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1484559774398804, "target_z": 1.5000000553932042, "ce": 6.229123115539551, "genuineness": 4.218649387359619, "identity": 0.5308205485343933, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2464f9256695aad6a6d16a61c9b4dded133f83b6f9d4ba085a29e7189c7a00f1.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "24684fbe93f0b23ffb398f01b2476ae57f2d664cf8887e96445b307c78993cf5", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c89a72a474f23698366a67e73c16e934e24aeb7ba15ebb036194db2ea4adce27", "generation_seconds_batch": 17.797230160911568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3409094512462616, "target_z": -0.0009765821905530657, "ce": 5.982900142669678, "genuineness": 3.948779582977295, "identity": 0.4470778703689575, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/24684fbe93f0b23ffb398f01b2476ae57f2d664cf8887e96445b307c78993cf5.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "24d5c94e81bb7db57cd6651c5c1a7521e9b341482747c9f0f19114f60a04564a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1488ea2a1d1da1e0649d28ebbf18579ac3429bc8c1f30104ed495364e46cd3e8", "generation_seconds_batch": 15.340113712009043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.79612398147583, "target_z": 4.562499986151699, "ce": 6.252951145172119, "genuineness": 4.049196243286133, "identity": 0.270898699760437, "hypothesis": "The door's still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/24d5c94e81bb7db57cd6651c5c1a7521e9b341482747c9f0f19114f60a04564a.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "252ad04aeb9edaacbbd11cd8162a9b6b45285bcf360c800b24ccc5ceda2286dd", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c0a9d7a8d5c1849312f9b15b18f22e03deb46884e536a488c2275ff507395c27", "generation_seconds_batch": 22.10513888206333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4847147464752197, "target_z": 2.125000027696602, "ce": 6.181467056274414, "genuineness": 3.9801597595214844, "identity": 0.16744214296340942, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/252ad04aeb9edaacbbd11cd8162a9b6b45285bcf360c800b24ccc5ceda2286dd.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "254087d12fab92bdd5305f61995d1a25d613c34f9ab13dc206bec73a33506e5b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "26d2b31209e9b388af3fe8223f1d0c99459652b02553a269d37e75a72f434fa4", "generation_seconds_batch": 22.723982324940152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.02272891998291, "target_z": 3.125000249269419, "ce": 6.165581703186035, "genuineness": 3.5816311836242676, "identity": 0.18869179487228394, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/254087d12fab92bdd5305f61995d1a25d613c34f9ab13dc206bec73a33506e5b.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": "25a4524a2689c2463b0816d65e5ea95d27d804011068be3ef0e9fd207e316deb", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4aa84fc98681e78efc8af6432435c7b60021ad8e65d8b5bded66144d335678a9", "generation_seconds_batch": 25.512392443954013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7032829523086548, "target_z": 2.5312500207724518, "ce": 6.427689552307129, "genuineness": 4.21237325668335, "identity": 0.2797786593437195, "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_Teasing/25a4524a2689c2463b0816d65e5ea95d27d804011068be3ef0e9fd207e316deb.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": "25d199f21f5ff8958daa3dde4228f7080e819b297f5ee98b4587b653c7d5e973", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7ef2cdda5bfa79077869f1d5dd54e4209ae23d5ecb032476a80f7508c2c76f13", "generation_seconds_batch": 19.03884321206715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3754305839538574, "target_z": 1.921874920372269, "ce": 6.427689552307129, "genuineness": 3.9550557136535645, "identity": 0.5743353366851807, "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_Teasing/25d199f21f5ff8958daa3dde4228f7080e819b297f5ee98b4587b653c7d5e973.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "2600ca15231c700cb9bbf0f05756aefc61de6e3841ab0f7e2f38d0cea1379ec7", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "678dcfa390ba01d758ca5f8d03f2664ac58d3cf9c93508ca703013de3b80f74d", "generation_seconds_batch": 23.32278904900886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8966317176818848, "target_z": 2.8906249549930214, "ce": 6.213237762451172, "genuineness": 3.973883628845215, "identity": 0.45402419567108154, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hin.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2600ca15231c700cb9bbf0f05756aefc61de6e3841ab0f7e2f38d0cea1379ec7.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "2641cc11814f8e47dfbcc0fba19a19b3edbc5f5f1492157ffc921007e2f560e0", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e75300ce8e9c8868244b54949ae4d965f26c1c654b1e5ad6366dcb9d3518f645", "generation_seconds_batch": 25.733510710066184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3586176633834839, "target_z": 1.8906249549930216, "ce": 6.197352409362793, "genuineness": 4.13078498840332, "identity": 0.2726653218269348, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2641cc11814f8e47dfbcc0fba19a19b3edbc5f5f1492157ffc921007e2f560e0.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "26b3fb7b49270015eeebdb5c15c6219b26dc4676d39f816c816efef2384af673", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1eb9ddd4aa44356c1f64becec4a5802ed2bdd1ce690c6ceec99654a9fc4b3e17", "generation_seconds_batch": 23.768547072075307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0475783348083496, "target_z": 1.312500041544903, "ce": 6.292664527893066, "genuineness": 4.18099308013916, "identity": 0.5454006195068359, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/26b3fb7b49270015eeebdb5c15c6219b26dc4676d39f816c816efef2384af673.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "e3fdd5313cfcedeb8efcc7b4a3da12fca051b68f75344cc3a64bb73925c2d4c6", "generation_seconds_batch": 17.580216636997648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09344401955604553, "target_z": -0.4609374878827366, "ce": 6.403861999511719, "genuineness": 4.262581825256348, "identity": 0.2654270529747009, "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_Teasing/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "26fa051bc8babd22953b9de3047a0632038b2855614843634c3e158628278f7a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b67ba339d681589b9ae69ddb10806b17b209a2e105276543bf5fdf3828534382", "generation_seconds_batch": 23.9024544400163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4679017066955566, "target_z": 2.093749840744538, "ce": 6.006728172302246, "genuineness": 3.898571252822876, "identity": 0.5641897916793823, "hypothesis": "La purez sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/26fa051bc8babd22953b9de3047a0632038b2855614843634c3e158628278f7a.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "2713faa57a15c9beca972773f8d13622b267e4d23db7338233ab32fabbe7a654", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b6c684e3a7bfbc9745a6c329af11700177da64e5d312ca2e4282a1112945a20a", "generation_seconds_batch": 21.505957082961686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6111817359924316, "target_z": 4.218750145407161, "ce": 5.982900142669678, "genuineness": 4.162164688110352, "identity": 0.241794154047966, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2713faa57a15c9beca972773f8d13622b267e4d23db7338233ab32fabbe7a654.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "27e2ecb05b55c8c185844803abcb698bf97b0ac6f8792bcb10bde431f38130a7", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "30db12c78a60997720684f329c257a58ce6f391b7e3c4d39701b08daae6285b9", "generation_seconds_batch": 24.56675198196899, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5775558948516846, "target_z": 4.156250214648666, "ce": 6.133810997009277, "genuineness": 4.068024158477783, "identity": 0.40654903650283813, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "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_Teasing/27e2ecb05b55c8c185844803abcb698bf97b0ac6f8792bcb10bde431f38130a7.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "27eceb6790450b2f46388ac17478516b422aaecddf2dbb1a10d2be949478e23c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1d9ef0076d9a013e9df388fd022f67d9556ba6f01d8a0d5bb21bc9ec7fecfe26", "generation_seconds_batch": 21.91457379097119, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5099340677261353, "target_z": 2.1718748649790647, "ce": 5.903473377227783, "genuineness": 3.8546390533447266, "identity": 0.46515265107154846, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/27eceb6790450b2f46388ac17478516b422aaecddf2dbb1a10d2be949478e23c.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "2829e0ecf15e8cb78046b287ad8336dec401e748bcd72c85ed04a63cbd992195", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4e6b6253052703d36bd5cb70e4df1987483a77e25ca0741ddff62276df48d525", "generation_seconds_batch": 21.633840478025377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.039171814918518, "target_z": 1.296874948068871, "ce": 6.23706579208374, "genuineness": 4.507347106933594, "identity": 0.7233293056488037, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2829e0ecf15e8cb78046b287ad8336dec401e748bcd72c85ed04a63cbd992195.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "28f8a239494b0b62e7a2021bc93a152eb11c1a648cd2d46664917b230e5c8ef8", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ead7af5ffd8d777ec31cffe53a4103906f6e0a3747c5b460b3b62b713918b328", "generation_seconds_batch": 23.53850200190209, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8545993566513062, "target_z": 2.8124999307584946, "ce": 6.252951145172119, "genuineness": 4.2249250411987305, "identity": 0.47712084650993347, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/28f8a239494b0b62e7a2021bc93a152eb11c1a648cd2d46664917b230e5c8ef8.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "2962a5a06462b770e4032940939522457b8c075980092ee6de77551874e9e14a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0e08ff39dbcdc530ec2d7765cbc7a7069ea4d8c1502a5dbdeca917ebb0438019", "generation_seconds_batch": 22.3555892650038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6948764324188232, "target_z": 2.5156249272964195, "ce": 6.038498878479004, "genuineness": 3.848362922668457, "identity": 0.43677279353141785, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2962a5a06462b770e4032940939522457b8c075980092ee6de77551874e9e14a.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "29d3546582fe63271e6e6a2eac7a45d64f5dde5967ee987e9996409381add912", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4483af9b7563c9a78a08abfa803a2bed8a6501a4477372d86b578251e3cae914", "generation_seconds_batch": 22.656764965038747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8416198492050171, "target_z": 0.9296875778966934, "ce": 6.046441555023193, "genuineness": 3.8922953605651855, "identity": 0.3996080160140991, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/29d3546582fe63271e6e6a2eac7a45d64f5dde5967ee987e9996409381add912.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "29dd62e6ddb27ceb2b3e2636612adaa6a6697e03cbcfd99ceb3e6c271d10000d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "38920e62dc289bdbc2d7d7710b21add793db000fe506e84cd6511c899d09cef8", "generation_seconds_batch": 21.768442295957357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3754305839538574, "target_z": 1.921874920372269, "ce": 6.062326908111572, "genuineness": 3.7291181087493896, "identity": 0.5321754813194275, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/29dd62e6ddb27ceb2b3e2636612adaa6a6697e03cbcfd99ceb3e6c271d10000d.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "2a086f96e5a4887f5cec84d5d4891649ebd4b90aba55fb7b7872178ceea56c4e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bf25b827be5e442d4f392c847502497576527fd2ce17bb08d9d71575eaaa3d31", "generation_seconds_batch": 25.095852859085426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09344401955604553, "target_z": -0.4609374878827366, "ce": 6.284721851348877, "genuineness": 4.3127899169921875, "identity": 0.5273721218109131, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2a086f96e5a4887f5cec84d5d4891649ebd4b90aba55fb7b7872178ceea56c4e.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "2a36039028512cf1242fd4d45ed032b2b21d5700bba92cee01f4fc5b0024f332", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "82bbc6698dfdba518be30863e7999afefa8cd200bd4b525c78e6f7f78b2a8f00", "generation_seconds_batch": 23.800618640030734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4931211471557617, "target_z": 2.140624899599817, "ce": 6.284721851348877, "genuineness": 3.8546390533447266, "identity": 0.3844951093196869, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2a36039028512cf1242fd4d45ed032b2b21d5700bba92cee01f4fc5b0024f332.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "2b2416988e09889b4358654a0f328a5bcec71c3ef8f610b20948fdda3f5e6860", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "99bb6cddfffa622969504844a9e965ee795a68cfaa0dd77800b377f2bd745950", "generation_seconds_batch": 23.338846137048677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4594953060150146, "target_z": 2.0781249688413226, "ce": 6.149696350097656, "genuineness": 3.7165660858154297, "identity": 0.2512018084526062, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2b2416988e09889b4358654a0f328a5bcec71c3ef8f610b20948fdda3f5e6860.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "2bbcb717a1baae47be0a943ab0ce54886c9ce573e850ccddc72bd77c2f3f538c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5b3790f7bbbbf939213fde01b38c2173b34f76f194a339a5d06cab63bb5ec4bc", "generation_seconds_batch": 18.0261860989267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5015276670455933, "target_z": 2.1562499930758494, "ce": 5.847874641418457, "genuineness": 3.7416701316833496, "identity": 0.5228561758995056, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2bbcb717a1baae47be0a943ab0ce54886c9ce573e850ccddc72bd77c2f3f538c.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": "2c0dd27ad7a70d11fc4a1453bbf656490f17bacc7239aecc1b4e4088b7c75d9d", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dbe6772329269e4855d1b18bb8e8fa981df0f8226da495d986b4054332e3656d", "generation_seconds_batch": 24.17679652001243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4847147464752197, "target_z": 2.125000027696602, "ce": 6.221180438995361, "genuineness": 4.105680465698242, "identity": 0.7701650261878967, "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": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2c0dd27ad7a70d11fc4a1453bbf656490f17bacc7239aecc1b4e4088b7c75d9d.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "2c5ea67d1d9ee0973255a33dd5ea760319e7f1f4d2625fc8ee14d5d8379e7c1e", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "43d4ecc471eb863a667320be305e3f9234afe51e929fa003336f28c9e7a1dec4", "generation_seconds_batch": 19.26268037094269, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5284788012504578, "target_z": 0.34765622489995435, "ce": 6.157639026641846, "genuineness": 3.9801597595214844, "identity": 0.2901732623577118, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2c5ea67d1d9ee0973255a33dd5ea760319e7f1f4d2625fc8ee14d5d8379e7c1e.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "2c7e28fbdb15f5655cf2d2db4639d5b1de7b09414a65df2040f6c53fc07ea64e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ee463b99f7f66ab9627d73ee04059e652c004f8307679fd0a49f0306eeefd974", "generation_seconds_batch": 17.00668077194132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1992647647857666, "target_z": 3.4531252181107415, "ce": 6.141753673553467, "genuineness": 3.9173994064331055, "identity": 0.3489798903465271, "hypothesis": "Heb het kleine doosje gevonden stond naast het oude raam. We kunnen daar samen in kijken.", "wer": 0.16666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2c7e28fbdb15f5655cf2d2db4639d5b1de7b09414a65df2040f6c53fc07ea64e.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "2cbb4221017895d5f55f9f594b1c2d226f761f999077e37ad770b36f07aa9910", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8a99107c21f2d9f3d3f2c33b8f3a870a9f03edd2efdd78cc242fc03d1d9d7e3d", "generation_seconds_batch": 15.369614523020573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6696569919586182, "target_z": 2.4687498684411397, "ce": 6.165581703186035, "genuineness": 4.143336772918701, "identity": 0.5535892844200134, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2cbb4221017895d5f55f9f594b1c2d226f761f999077e37ad770b36f07aa9910.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "2cde592b5b5dbb166cd662a5d57da67f862f60fdf1ec6360f3dcd5382f98e5fa", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "09aad4966cb0e525b7a810ca1dfd3f8565e205c360f5e6cf5bfa03fe492c3b6a", "generation_seconds_batch": 24.907558926963247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9218511581420898, "target_z": 2.937500013848301, "ce": 6.205295085906982, "genuineness": 3.6287014484405518, "identity": 0.43496888875961304, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2cde592b5b5dbb166cd662a5d57da67f862f60fdf1ec6360f3dcd5382f98e5fa.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "2cf06d31b8f1ebcc090af051e454ec300e644a98ca29c3e7b045c6c7a524ee3b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6cc6563be6c2e9110f5ce97c6b5f21b0e7497ed5a2ea15b64179d9dd74af2c89", "generation_seconds_batch": 22.252084524021484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.039541721343994, "target_z": 3.1562499930758494, "ce": 5.911416053771973, "genuineness": 3.8797430992126465, "identity": 0.16293616592884064, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2cf06d31b8f1ebcc090af051e454ec300e644a98ca29c3e7b045c6c7a524ee3b.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "2d4a6ed81535c6e3330094106b98d1a44538d0c8f1b6e88c584f0d98e2dd3df4", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "40f4f776f16a24724cdda136ef68efc9e087a485fa5e87c5277d113a1c441010", "generation_seconds_batch": 21.06776524905581, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3039755821228027, "target_z": 1.789062401330855, "ce": 6.09409761428833, "genuineness": 4.099404335021973, "identity": 0.6011696457862854, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2d4a6ed81535c6e3330094106b98d1a44538d0c8f1b6e88c584f0d98e2dd3df4.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "2d65ec538418db370c804f161f034ca52fc936aebcc9e35445ec00576a95d15b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8f74d5cdd79d6567c26b52774878c33b86f43d708dcf9223ae068dba37712dad", "generation_seconds_batch": 23.505177501938306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1922200322151184, "target_z": -0.27734374740344353, "ce": 6.332377910614014, "genuineness": 4.168440818786621, "identity": 0.4095371961593628, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2d65ec538418db370c804f161f034ca52fc936aebcc9e35445ec00576a95d15b.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "2de01c009929eaf4942257041bdd3b68c3b6f0af9dde899026a2e4dab2ed3934", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "14d2bea4ad572de33758a707e24a84a69d958721ecc3388e57d59b3a76f92795", "generation_seconds_batch": 26.4666938430164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2787562608718872, "target_z": 1.7421875640483924, "ce": 6.0305562019348145, "genuineness": 3.898571252822876, "identity": 0.5658354759216309, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2de01c009929eaf4942257041bdd3b68c3b6f0af9dde899026a2e4dab2ed3934.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "2e50d270b05c8174c0f4ad5cf31c7805145d794ffa860e67632f33bf9eb13297", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5acb04253b5098c991d95cc7d7212c6ccd723096bc3fa46e070075f3bc3025bb", "generation_seconds_batch": 16.6727786839474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2451303005218506, "target_z": 1.6796874117170808, "ce": 6.284721851348877, "genuineness": 3.873466968536377, "identity": 0.5081406831741333, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2e50d270b05c8174c0f4ad5cf31c7805145d794ffa860e67632f33bf9eb13297.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "2e9b5924510c7543f9f823916c8b816269f2d0f20a0305fa59d2e7e9fadaf3f6", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "cae19bdd88b04b775f776268c28de8981535f3374ad40ab9ecbcea07300446fd", "generation_seconds_batch": 16.33112779504154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8633759021759033, "target_z": 4.687500290814322, "ce": 6.078212261199951, "genuineness": 4.093128204345703, "identity": 0.49848508834838867, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2e9b5924510c7543f9f823916c8b816269f2d0f20a0305fa59d2e7e9fadaf3f6.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "2f6f19fd50f34c3584b15f607830030e94d0d5cda23e9077616fe6ebd59f6ac2", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5257ef801fce36b7c5249e7f8b17ccf416cd071f992db251e1636153a14467dc", "generation_seconds_batch": 23.338846137048677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.333768129348755, "target_z": 3.7031249411447207, "ce": 6.221180438995361, "genuineness": 3.848362922668457, "identity": 0.3065628111362457, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2f6f19fd50f34c3584b15f607830030e94d0d5cda23e9077616fe6ebd59f6ac2.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "2fa7e541270c7064644ebe4c4811a6abf7640865ea93516be6940c40077ad06c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d159e8cf1aec35bf847ba026a4a160b2426138fa698f522f907e6c08c3c17226", "generation_seconds_batch": 21.590204150998034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.443052291870117, "target_z": 3.9062500484690537, "ce": 5.982900142669678, "genuineness": 3.6914620399475098, "identity": 0.5623453855514526, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2fa7e541270c7064644ebe4c4811a6abf7640865ea93516be6940c40077ad06c.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "2fe951c505034ab40618ff2711af905a9949ab80cd50d8256a059a5b8ef5eb67", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6fdb4bb958e1c31f9e47fbc3f4a62ea99aa87ca0df7aa0af8df50a9bb473724f", "generation_seconds_batch": 23.548563453019597, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6444376707077026, "target_z": 2.4218750311586774, "ce": 6.165581703186035, "genuineness": 3.653805732727051, "identity": 0.4196721613407135, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/2fe951c505034ab40618ff2711af905a9949ab80cd50d8256a059a5b8ef5eb67.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "3012141ae45fa76de9dd1724111b2978960a1994fc5858496e8a92aa6ea30a5c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "27bdd2cc56cde8dfb480ab2e699722a659972e010f4c76cfe1be1967f06fbb22", "generation_seconds_batch": 21.085924029001035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.678433418273926, "target_z": 4.34375000692415, "ce": 6.173524379730225, "genuineness": 3.6977379322052, "identity": 0.2650357484817505, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3012141ae45fa76de9dd1724111b2978960a1994fc5858496e8a92aa6ea30a5c.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "3023cedf71cb0ff34e145e25c6ee5e361b02a4d3540e4cee24af9694752fe442", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e6429795da30179f68447317f6d546bcbd78594f8e3c638d21a86fa6166ae925", "generation_seconds_batch": 24.530380088021047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8633759021759033, "target_z": 4.687500290814322, "ce": 6.1894097328186035, "genuineness": 4.137060642242432, "identity": 0.34264665842056274, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3023cedf71cb0ff34e145e25c6ee5e361b02a4d3540e4cee24af9694752fe442.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "302e27d9bf65f650b153e4133dd40e7d88dcff3cc394411cdfc509d1e63422cb", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f23141eced8b78754c3d3afb52d28dfb640a729773563d18c81fe82016625706", "generation_seconds_batch": 24.027742718928494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8041605949401855, "target_z": 2.7187500346207525, "ce": 6.308549880981445, "genuineness": 4.287685871124268, "identity": 0.4167333245277405, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/302e27d9bf65f650b153e4133dd40e7d88dcff3cc394411cdfc509d1e63422cb.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "3071e97b092d6fedacfdbb71c3b958ee6f6477fd73e615d1ab4168c486160d28", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fcc8e03d939ba1c35ba9a50258925c39cb4bace43508fb421ea304edcf263c67", "generation_seconds_batch": 22.16124658600893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8248068690299988, "target_z": 0.8984375017310376, "ce": 6.356205940246582, "genuineness": 4.268857479095459, "identity": 0.47900378704071045, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3071e97b092d6fedacfdbb71c3b958ee6f6477fd73e615d1ab4168c486160d28.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "30d03833757ce8b4f02c101089c346708cc0cbae3108fbcac4401a7c77c29e1f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0d95023901357720990eccaec4797fddc4fdd408a37c11a08ed0ad9a4c6bb55c", "generation_seconds_batch": 26.61520223901607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4006500244140625, "target_z": 1.9687499792275485, "ce": 5.935244083404541, "genuineness": 3.747946262359619, "identity": 0.5084480047225952, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/30d03833757ce8b4f02c101089c346708cc0cbae3108fbcac4401a7c77c29e1f.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "30d76f1b46e9793e828d633524cd1d0a8a4537f67d1718475b78f83a2c816dcf", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b720082fef53ca23f768693347558466cd015f74a118eb0a1174f01d31a59147", "generation_seconds_batch": 25.797876174096018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6276246309280396, "target_z": 2.390624844206613, "ce": 5.879645347595215, "genuineness": 4.030367851257324, "identity": 0.45323848724365234, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/30d76f1b46e9793e828d633524cd1d0a8a4537f67d1718475b78f83a2c816dcf.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "313486cd8839910f8940d85dad4c52e0a6620a9af3173a1833dbf91ea8c1680a", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6668389a587850580d2716e055988a640b478d0162a1a0528bf00d1c964b52f3", "generation_seconds_batch": 18.3912093230756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5431901216506958, "target_z": 0.3749999723033979, "ce": 6.23706579208374, "genuineness": 4.256305694580078, "identity": 0.6909012198448181, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/313486cd8839910f8940d85dad4c52e0a6620a9af3173a1833dbf91ea8c1680a.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "3240141a3605165eaa32c23dd7433d29e9e11b3eb13f115de84243ca83abe1cc", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "abecb440b28a3f82dbbdbd464f9236912be09e1a3fb5df1ca61d8956478b4deb", "generation_seconds_batch": 26.177133386954665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6587790846824646, "target_z": 0.5898437335551425, "ce": 6.038498878479004, "genuineness": 4.168440818786621, "identity": 0.685697078704834, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3240141a3605165eaa32c23dd7433d29e9e11b3eb13f115de84243ca83abe1cc.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "3374818f017c86e2ae93c0a6073b46959426719c4149f0ce88acf0aac899f2ac", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "10e0c698aaeca90da4105c0a4a031fbb691a0d25b6e00bc0385c8f199dab98d8", "generation_seconds_batch": 24.032204068033025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3460079431533813, "target_z": 1.8671874255653818, "ce": 6.38003396987915, "genuineness": 4.080576419830322, "identity": 0.5456423759460449, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3374818f017c86e2ae93c0a6073b46959426719c4149f0ce88acf0aac899f2ac.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "338c2afb1da576dc7233155b1337a7dff703d8abaa2f5a0d99b46b86095d68b1", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e7acc16171ecb52ef40a622e0c9bfaaa2315ffa70f1f858393bd6f17588ed838", "generation_seconds_batch": 16.80379750893917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.762128233909607, "target_z": 2.6406250103862257, "ce": 5.927301406860352, "genuineness": 3.9048471450805664, "identity": 0.33969563245773315, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/338c2afb1da576dc7233155b1337a7dff703d8abaa2f5a0d99b46b86095d68b1.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "338f972ad53c37d254eb840094323e47bb269b5c52d872ab67032ef69008445e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "6580ca8a139d4d5ecd82148c3f4065d99dcdd68cb2637c0fada2cc0f76fe58e5", "generation_seconds_batch": 17.67884777497966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5267471075057983, "target_z": 2.203125051931129, "ce": 6.23706579208374, "genuineness": 4.331617832183838, "identity": 0.42342454195022583, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen daar samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/338f972ad53c37d254eb840094323e47bb269b5c52d872ab67032ef69008445e.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "33bd1226d7ca5ecb241889a1a90a590958c680214b343c62557d5e79272b241b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 125, "seconds_generated": 10.0, "mp3_sha256": "e8005617a6deed90296e3fa8cf6736af9f16f0962840fc05509a2c7fcf1a2442", "generation_seconds_batch": 22.788364767911844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6528440713882446, "target_z": 2.4374999030618927, "ce": 5.982900142669678, "genuineness": 3.653805732727051, "identity": 0.4478911757469177, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemein.", "wer": 0.125, "duration_error_s": 0.1999999999999993, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/33bd1226d7ca5ecb241889a1a90a590958c680214b343c62557d5e79272b241b.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "33c98ed0c1af4daa0bfd7de91b30e147521d29306f732fa355f3e2d208dcf376", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8cc0ea47d217b51264e71b13fadfeb6a3041b12c40b8e5ff713ced297bfc8102", "generation_seconds_batch": 23.35840481496416, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5435600280761719, "target_z": 2.2343750173103762, "ce": 6.3641486167907715, "genuineness": 3.8546390533447266, "identity": 0.400881826877594, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/33c98ed0c1af4daa0bfd7de91b30e147521d29306f732fa355f3e2d208dcf376.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "33d74d8e5ccee6370f5e4d0cd98313cd2ed560b1bf6e7399c5480eac55c8f087", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ff3aeb92c46d2a0b9a9c86970aa97cd5feb0a0dd48e8abc07bb83c0b82d236df", "generation_seconds_batch": 16.514878269983456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4594953060150146, "target_z": 2.0781249688413226, "ce": 6.109982967376709, "genuineness": 4.137060642242432, "identity": 0.6513171195983887, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/33d74d8e5ccee6370f5e4d0cd98313cd2ed560b1bf6e7399c5480eac55c8f087.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "91bcbd1999bf4a3081cccaa8d58a4b437de0607b3a9d67e416e26c9e2c4cc9be", "generation_seconds_batch": 19.514894305029884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4927513003349304, "target_z": 0.28124996537924735, "ce": 6.125868320465088, "genuineness": 4.3504462242126465, "identity": 0.8070470094680786, "hypothesis": "De weg gaat linksaf naar de brug. Loopt verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "344f8f00f6b9b682a99e7035e0800dec84c083adc9b471a9f7170c5ab8ed643c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e6d848866b8a0ebd9b510e68238de7c9e8a50356c2d80507d726f445b22c5fc4", "generation_seconds_batch": 23.61997099907603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.795754075050354, "target_z": 2.7031249411447207, "ce": 6.062326908111572, "genuineness": 3.587907314300537, "identity": 0.4983891248703003, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/344f8f00f6b9b682a99e7035e0800dec84c083adc9b471a9f7170c5ab8ed643c.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "346c6525edce479a7fd35fe873fea8da8e3e9cf5d6beaa6af606f211aa6b32f8", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b54f8dd14c3c21d17b87cf24325db0eb97d6eea37907a56d7842961c14c39595", "generation_seconds_batch": 23.91805508104153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5271170139312744, "target_z": 4.062500096938107, "ce": 5.911416053771973, "genuineness": 3.9173994064331055, "identity": 0.6091835498809814, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/346c6525edce479a7fd35fe873fea8da8e3e9cf5d6beaa6af606f211aa6b32f8.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "2882545d9b2ed5c27df70d59cb55688d05f31fbb49a83b62e0534bf217e2016b", "generation_seconds_batch": 16.264178700046614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.080834299325943, "target_z": -0.4843750173103763, "ce": 6.459460258483887, "genuineness": 3.961331605911255, "identity": 0.37710198760032654, "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_Teasing/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "349217535028bce9260959a65f857d5905d5baf1d730bdc26d6ddd0471ed0fb6", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "94873fe2101a72347a4c6c830e8b42a9774c4f2d3e5cecc48709b9600813c5ff", "generation_seconds_batch": 17.629988386062905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7407422065734863, "target_z": 0.7421875640483924, "ce": 6.213237762451172, "genuineness": 4.375550270080566, "identity": 0.5737007856369019, "hypothesis": "Je trouvais la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/349217535028bce9260959a65f857d5905d5baf1d730bdc26d6ddd0471ed0fb6.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "3507e65ed9bd6afb7b07f1d803d12ff68491bda85e18d35fddfa4ef176c709a5", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d8af6ce398cbbec7c421c6b5a02d07605220b0e10b97d7caac66e27eee763761", "generation_seconds_batch": 24.529667459079064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2160775661468506, "target_z": 3.484374961917172, "ce": 6.125868320465088, "genuineness": 3.653805732727051, "identity": 0.2535461485385895, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3507e65ed9bd6afb7b07f1d803d12ff68491bda85e18d35fddfa4ef176c709a5.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "35f63f03757f64aad12246a21b04988593a401abfab774ef41d0e8b17f7a1650", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b98f59251c3b9b2d0a3a230527c5d1c402cd0489f11658844ba283f5f9d35fee", "generation_seconds_batch": 25.75701088400092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23530319333076477, "target_z": -0.1972656141810148, "ce": 6.173524379730225, "genuineness": 4.15588903427124, "identity": 0.7488311529159546, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/35f63f03757f64aad12246a21b04988593a401abfab774ef41d0e8b17f7a1650.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "372f9d5dd5e0b0f3200df59d5a27f64874f821d124e1550fd7c7b5947a4ba2c1", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8d965043d1f073c8277cc35ec6756fbbfb049f8e8302f2c51aa3044c60a01b9f", "generation_seconds_batch": 24.002939373953268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8882251977920532, "target_z": 2.8749998615169896, "ce": 6.038498878479004, "genuineness": 3.7918784618377686, "identity": 0.5495856404304504, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/372f9d5dd5e0b0f3200df59d5a27f64874f821d124e1550fd7c7b5947a4ba2c1.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "3771f568d37508749dc017d8fbe152301d78b41a6ec1f674b7543a3e6ace1ee9", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "26a03375164312252e70f4475326634ab035f0bcd6a2f44c6964abcd1cc93405", "generation_seconds_batch": 15.625592457014136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.678433418273926, "target_z": 4.34375000692415, "ce": 6.149696350097656, "genuineness": 4.168440818786621, "identity": 0.3731997013092041, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3771f568d37508749dc017d8fbe152301d78b41a6ec1f674b7543a3e6ace1ee9.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "3813808bbff718fa39d82723c99f8b0e2869273d7bc9734207093a62113ef06a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c82f8cbafeee7f2d7ce5835bea75f7cb4549a9d340b699712458f9ba6510c28a", "generation_seconds_batch": 23.622062790906057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8416198492050171, "target_z": 0.9296875778966934, "ce": 6.324435234069824, "genuineness": 4.356721878051758, "identity": 0.2457398772239685, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3813808bbff718fa39d82723c99f8b0e2869273d7bc9734207093a62113ef06a.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": "386accc2ffafcaa28d310e8142e1c213f287a6773a1724dbb8747b65643529c4", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4d0c5a2bc00e937cc4e27c390ddd8d66ad6b1da6bed66dd4366cf019acb8b520", "generation_seconds_batch": 17.65179327002261, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7071163058280945, "target_z": 0.6796875225034892, "ce": 6.054384231567383, "genuineness": 3.7542223930358887, "identity": 0.553534209728241, "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_Teasing/386accc2ffafcaa28d310e8142e1c213f287a6773a1724dbb8747b65643529c4.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "38dcda5d9b777c0f29a7b48175da0266bae2d0c80454572024eb8650f500ba52", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c772b49b7b4b8ed26433ec852b33f8dba9692211b1a8ef8a7187a21995bdd2b7", "generation_seconds_batch": 26.72880255698692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.417832851409912, "target_z": 3.8593749896137743, "ce": 6.205295085906982, "genuineness": 4.218649387359619, "identity": 0.21362218260765076, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/38dcda5d9b777c0f29a7b48175da0266bae2d0c80454572024eb8650f500ba52.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "3928e08fcda9529c0137213ab9aacb238d0e33be6440181337d4802ee8e8440d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "464b99b9a1b6001d63a045f938f43eb8cac9da0d359026a2d3eb68ecb3d9eb60", "generation_seconds_batch": 24.01766341191251, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.316955327987671, "target_z": 3.67187519733829, "ce": 6.2767791748046875, "genuineness": 4.293961524963379, "identity": 0.5500158071517944, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3928e08fcda9529c0137213ab9aacb238d0e33be6440181337d4802ee8e8440d.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "39385c147629231c1eb37f4d1879e6998fc8785e190297c7f9b214d6999e92cb", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7c7b0eec55d08fdba5163ec3614c66266b133c2b4f2543151b9975d5f1af2181", "generation_seconds_batch": 17.629988386062905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.039171814918518, "target_z": 1.296874948068871, "ce": 6.348263263702393, "genuineness": 4.2249250411987305, "identity": 0.6974306106567383, "hypothesis": "Eh, j'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/39385c147629231c1eb37f4d1879e6998fc8785e190297c7f9b214d6999e92cb.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "39af0ce3331780bf7a99960f4f8cf2764cca0ca452961dc03fc4e0ed0da9ea11", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9f1f5d2a14c64be85e52e65d2b5c3d0a30a56ee7d61f71071631ed07917bcd46", "generation_seconds_batch": 24.516981432097964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.005545973777771, "target_z": 1.2343750173103762, "ce": 6.23706579208374, "genuineness": 4.111956596374512, "identity": 0.6411212086677551, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/39af0ce3331780bf7a99960f4f8cf2764cca0ca452961dc03fc4e0ed0da9ea11.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "3a15cba350df44721b63988aa753f84b4fb0281f8df7c2882fb55e4825071120", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4d809842e4d239e32c4652d01b6eac7e2359a41448ee9088550d6d211887b609", "generation_seconds_batch": 27.707844900083728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2325206995010376, "target_z": 1.656250103862258, "ce": 5.6254801750183105, "genuineness": 3.785602569580078, "identity": 0.7414067983627319, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3a15cba350df44721b63988aa753f84b4fb0281f8df7c2882fb55e4825071120.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": "3a27a46cef2defcf6b03e7de6d3e3e98e458935290a14a021bcd6ee43f4a9635", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "39fa0f5024cfb736045de0974002d913ecf1bc97d9634fd04c3ea8a7ad3128d7", "generation_seconds_batch": 24.129037444014102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6780635118484497, "target_z": 2.484374961917172, "ce": 6.125868320465088, "genuineness": 4.532451152801514, "identity": 0.7431243658065796, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-le bien et vérifie les deux derniers chiffres. Appelle-moi quand il y aura un moment.", "wer": 0.13636363636363635, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3a27a46cef2defcf6b03e7de6d3e3e98e458935290a14a021bcd6ee43f4a9635.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "3a8249f7fc776da3c5e10ff55c638dad3b4e1365ba0141e791adddabf4863ef7", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f90230aadefdf39bf9b4914fdea25162befb3aa30c6f4a284e4af39421fcdf7e", "generation_seconds_batch": 23.212998990085907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1236064434051514, "target_z": 3.312500041544903, "ce": 6.165581703186035, "genuineness": 3.9299514293670654, "identity": 0.45600688457489014, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3a8249f7fc776da3c5e10ff55c638dad3b4e1365ba0141e791adddabf4863ef7.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "3ad51286134eef2cc99e6fef05e0c15b0665ad362aa6aa97dcfb3e7158ca73c5", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "837b165e40640deec55773bb826b4c529fc4294b0ae4fd72db0a291b3aeb5a48", "generation_seconds_batch": 23.041949163074605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.829379916191101, "target_z": 2.7656248719032153, "ce": 6.062326908111572, "genuineness": 4.042920112609863, "identity": 0.5819252133369446, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3ad51286134eef2cc99e6fef05e0c15b0665ad362aa6aa97dcfb3e7158ca73c5.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": "3ae00c2c47211517f31b3ca6dce8459c24451954b13c8da8edecb5f02f13f7fc", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c8d16acd5ac8c0f7e70da081827ccf206130d976e6f89da1a5daea4e9347e2de", "generation_seconds_batch": 25.331630119937472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.030765414237976, "target_z": 1.2812500761656558, "ce": 6.348263263702393, "genuineness": 3.6851859092712402, "identity": 0.4059266746044159, "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_Teasing/3ae00c2c47211517f31b3ca6dce8459c24451954b13c8da8edecb5f02f13f7fc.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "3ae60de6efb07b3f9c489bc3603ee8dbe298c71acedbb66f2c7801e92c217fa0", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6e9dea447f5530a8867105f7b6713eb32073f95b847d5947d1d1412c239e8215", "generation_seconds_batch": 24.530380088021047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5607428550720215, "target_z": 4.125000027696602, "ce": 6.1894097328186035, "genuineness": 4.20609712600708, "identity": 0.42301440238952637, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3ae60de6efb07b3f9c489bc3603ee8dbe298c71acedbb66f2c7801e92c217fa0.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": "3b303ed6d26e853422f5062f3c5a6464af75b4f23c2f50c9728a610ed41e18c5", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d9421d90c921e6f40a62a9cf987b4587ed252a6fef8dc2c7a0bd783a3f428690", "generation_seconds_batch": 19.887559960014187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4594953060150146, "target_z": 2.0781249688413226, "ce": 6.054384231567383, "genuineness": 4.193545341491699, "identity": 0.6805510520935059, "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_Teasing/3b303ed6d26e853422f5062f3c5a6464af75b4f23c2f50c9728a610ed41e18c5.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "3b5d20ce3edc86e758551a92c745b10fbf6ccd7671f267552c6e953dcf3c454d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4c259ce4c696d2c6f6b120e3ec288b062e4fb5f001e6870193ddc72a1897213b", "generation_seconds_batch": 25.157836435944773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7113195657730103, "target_z": 0.6875000692415053, "ce": 6.133810997009277, "genuineness": 4.281409740447998, "identity": 0.6299724578857422, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3b5d20ce3edc86e758551a92c745b10fbf6ccd7671f267552c6e953dcf3c454d.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": "3b75c341f4fb824bc6f59c8e0afcddf4cdecdc0628979d025a26bc03756c4dcb", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "097df819200424b9aae7ee408c7f87fa15e3d57ed036a041439d249e52defdc2", "generation_seconds_batch": 22.39494717400521, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9386640787124634, "target_z": 2.9687499792275482, "ce": 6.308549880981445, "genuineness": 4.15588903427124, "identity": 0.6385979652404785, "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_Teasing/3b75c341f4fb824bc6f59c8e0afcddf4cdecdc0628979d025a26bc03756c4dcb.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": "3c3ba1b461f95c87de30c3a8b7520dfe602252a2a776e3e4ec7b12411aa1f5c5", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1c2a50f1aa9634fa5d31d62b71383219e3f0125b116af651cb30a4c9cd54199d", "generation_seconds_batch": 14.928362309001386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3796337842941284, "target_z": 1.9296873563238766, "ce": 6.23706579208374, "genuineness": 4.444586753845215, "identity": 0.502088725566864, "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_Teasing/3c3ba1b461f95c87de30c3a8b7520dfe602252a2a776e3e4ec7b12411aa1f5c5.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "3c527f32043d19878d5f5144702cb3024ab8a34c4d60b227522cc91c8bbe4e17", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "60c8baf6949070f46b775d57630c0394a1ca14553a565211c22dea195563a39a", "generation_seconds_batch": 17.322935087024234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1320128440856934, "target_z": 3.3281249134481183, "ce": 6.173524379730225, "genuineness": 3.6287014484405518, "identity": 0.4320458769798279, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3c527f32043d19878d5f5144702cb3024ab8a34c4d60b227522cc91c8bbe4e17.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "3045f7875807e02cee963cb3525e673389c33f00c89b43f54fd5f541053cc27e", "generation_seconds_batch": 19.941399262053892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2153378278017044, "target_z": -0.2343749896137742, "ce": 5.998785495758057, "genuineness": 4.105680465698242, "identity": 0.4446544647216797, "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_Teasing/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "3c8a9a0930c630128fb2372b0b03e7175b398f546c282ffa3916c69a085536ec", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "50b757046df2c834660e8857573c67687d1243922c9a611bbb673e9955820cfb", "generation_seconds_batch": 24.032204068033025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.030765414237976, "target_z": 1.2812500761656558, "ce": 6.427689552307129, "genuineness": 3.9801597595214844, "identity": 0.6056896448135376, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3c8a9a0930c630128fb2372b0b03e7175b398f546c282ffa3916c69a085536ec.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "3cf6b1e3bbf6d1b711700cfa66c18c8e333ec795268b9ad53736c49fa02d7c2e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6d24debe639c6f751e50120e5e2397ce4a6cd70e953330773737b49930d91187", "generation_seconds_batch": 26.428511556005105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3165853023529053, "target_z": 1.8124999307584948, "ce": 6.157639026641846, "genuineness": 4.369274139404297, "identity": 0.600547194480896, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3cf6b1e3bbf6d1b711700cfa66c18c8e333ec795268b9ad53736c49fa02d7c2e.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "3d4fb91da27b408c79ce195c81eb1f8adae3b186f51155789a3513fe5b417111", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b96e5926159423b72544e3b436f59e428acdaaa59ffc9e463cef0b1feaa42c21", "generation_seconds_batch": 22.378803233033977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0563547611236572, "target_z": 3.187500180027914, "ce": 5.728734970092773, "genuineness": 4.074300289154053, "identity": -0.004124850034713745, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3d4fb91da27b408c79ce195c81eb1f8adae3b186f51155789a3513fe5b417111.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "3d55aa6fc773402c5baf6c0b0e4ba5ad19651369db04cd2e1707d5951b55ceee", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e74988de2bc2ba359507a4ed1b0956698f473dd12934cc329121aa43a38a5a56", "generation_seconds_batch": 26.008283275994472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5015276670455933, "target_z": 2.1562499930758494, "ce": 6.292664527893066, "genuineness": 4.469690799713135, "identity": 0.664411187171936, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3d55aa6fc773402c5baf6c0b0e4ba5ad19651369db04cd2e1707d5951b55ceee.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "3d86aef0e10ead60aec0b7acb9b296f49f27a2ef9b159ac23a784bf59679a353", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "93ac71796165dd0d29bd724579a033bd2b627da423290bd6a4d7c17159d23b10", "generation_seconds_batch": 22.643289708998054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8041605949401855, "target_z": 2.7187500346207525, "ce": 6.09409761428833, "genuineness": 4.143336772918701, "identity": 0.5767337679862976, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3d86aef0e10ead60aec0b7acb9b296f49f27a2ef9b159ac23a784bf59679a353.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "3d93b98b2164bc1bfb60cc6858398bf1e3d088e6dfd520802dab977a77b20be2", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c3c9964720e120a3ce24a37d62a9da0bc8b7aba4b8cf9f80fd7d2407f158a85c", "generation_seconds_batch": 33.10968038300052, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4090564250946045, "target_z": 1.9843748511307637, "ce": 6.173524379730225, "genuineness": 3.7416701316833496, "identity": 0.2954726815223694, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3d93b98b2164bc1bfb60cc6858398bf1e3d088e6dfd520802dab977a77b20be2.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": "3f01f2062ca44ad071607d27853a46b002dc78519007ca98300ab66dbc1f9ee8", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ee6e615677967dd95999540e0fb822977561830e8dd881aa4eee3518a598f5f0", "generation_seconds_batch": 25.4711670440156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0475783348083496, "target_z": 1.312500041544903, "ce": 6.41180419921875, "genuineness": 4.231201171875, "identity": 0.5480659008026123, "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_Teasing/3f01f2062ca44ad071607d27853a46b002dc78519007ca98300ab66dbc1f9ee8.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "3f702d6335a0dc3303d7b59089df90027008d1c08b9b62ebbe994815d67d9b4c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bb4ed345f9223dbac2a54760eda604242d7a6bce6aa4cd19310e584a6cd5856d", "generation_seconds_batch": 26.4666938430164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.224114179611206, "target_z": 1.6406250103862259, "ce": 5.990842819213867, "genuineness": 3.9927117824554443, "identity": 0.4728271961212158, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3f702d6335a0dc3303d7b59089df90027008d1c08b9b62ebbe994815d67d9b4c.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "3f726a3f6e20ba6f19a6da7e1cc1ef24d9d75feb2a9781d83280cbfe350f9a3b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7b3605eda48dd2427df870b6a84d00e6e06916a8e4efb3aedbfb689ce474d1af", "generation_seconds_batch": 24.56082910404075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.955476999282837, "target_z": 2.9999999446067958, "ce": 5.871703147888184, "genuineness": 3.848362922668457, "identity": 0.6325274705886841, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3f726a3f6e20ba6f19a6da7e1cc1ef24d9d75feb2a9781d83280cbfe350f9a3b.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "3fa3bf891b16e8ae34e6687fd0648ce2c187c0e97a4f147e02a52d062f12a112", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "23d0303d4edf81d949552372b325befc7194a0e55d9f358ee51d24eb8cc0c640", "generation_seconds_batch": 20.06594318698626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3586176633834839, "target_z": 1.8906249549930216, "ce": 5.673136234283447, "genuineness": 3.4686625003814697, "identity": 0.6013420224189758, "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_Teasing/3fa3bf891b16e8ae34e6687fd0648ce2c187c0e97a4f147e02a52d062f12a112.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "3fbdc5ad4842710e1c7218bd9cf788c38b954fedbba77c85021be91ebe41a050", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a06fc206861e817a9afcaa308d9a808c86ffe5f5e0bfbfad2b9c6384b14a2cf0", "generation_seconds_batch": 27.707844900083728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.190488338470459, "target_z": 1.578125079627731, "ce": 6.3641486167907715, "genuineness": 3.6914620399475098, "identity": 0.3729625940322876, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/3fbdc5ad4842710e1c7218bd9cf788c38b954fedbba77c85021be91ebe41a050.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "40165717a4b0e8f2875e6cc1d95f82a1413a18416121e2d2b877f44d573ad158", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "083a6e34a1061f19c05fec618a784766c189e7b896801eca88857da7200a2611", "generation_seconds_batch": 18.823554044007324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9638835191726685, "target_z": 3.015625038082828, "ce": 5.689021587371826, "genuineness": 4.2374773025512695, "identity": 0.11830368638038635, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/40165717a4b0e8f2875e6cc1d95f82a1413a18416121e2d2b877f44d573ad158.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "4082bb51e7d66c42ab35a52ada1f606fe10de89be4951699edd1916a4c65a536", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fd0ccc2d9a281742c48490c2e1baafcce9a0690ceceeee92151b4e6639df4b8b", "generation_seconds_batch": 25.2451731209876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0812041759490967, "target_z": 1.3749999723033979, "ce": 6.403861999511719, "genuineness": 4.168440818786621, "identity": 0.6623718738555908, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4082bb51e7d66c42ab35a52ada1f606fe10de89be4951699edd1916a4c65a536.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "40f06a891a8dfbf5626bd6025dca0500b7fcf43e2ede127cb716d0cc3b6aec3e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ba00d7e07a2af6be06e8b0496ea5d5add6b0bb9c6c51171bc0121b97565ea462", "generation_seconds_batch": 22.502354993019253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.014322280883789, "target_z": 3.10937493422057, "ce": 5.982900142669678, "genuineness": 3.911123275756836, "identity": 0.33285319805145264, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/40f06a891a8dfbf5626bd6025dca0500b7fcf43e2ede127cb716d0cc3b6aec3e.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "4221cd282daa89c30e47be654026d9db39be1437bfe3587b3770fd55bfac999d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "bb35978337d4f4a2d90f809fe77efa1652d629520a7d015ef262536dba350697", "generation_seconds_batch": 23.594159456901252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5894256830215454, "target_z": 0.46093743248953234, "ce": 6.300607204437256, "genuineness": 3.9927117824554443, "identity": 0.49926576018333435, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4221cd282daa89c30e47be654026d9db39be1437bfe3587b3770fd55bfac999d.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "427d0221ee3cb9f1ded785567bfd718c4c763c8d1c6ccc37c9dfccceb38ac19e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "02aa87e703f40ffe7541795fe6c5b1d2f54359a14d8e20a1ac76db972256d339", "generation_seconds_batch": 24.99491029290948, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09764724969863892, "target_z": -0.45312499653792476, "ce": 6.23706579208374, "genuineness": 4.268857479095459, "identity": 0.5493923425674438, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/427d0221ee3cb9f1ded785567bfd718c4c763c8d1c6ccc37c9dfccceb38ac19e.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "42a353aa16007f22b87922a20d1ac7ad92717c1304a7ea3a32a58d974987c3df", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "30a451124f2df587f3eba37c9f7358eff3a6ca5b290350a6d17809d21b846ef7", "generation_seconds_batch": 22.81505403597839, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1404194831848145, "target_z": 3.3437502284969676, "ce": 6.054384231567383, "genuineness": 4.024092197418213, "identity": 0.46346598863601685, "hypothesis": "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_Teasing/42a353aa16007f22b87922a20d1ac7ad92717c1304a7ea3a32a58d974987c3df.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "f854da3292a57dfa0d8a62cfee399cdd78a9eec3787109a7ad552a86ab79e115", "generation_seconds_batch": 19.514894305029884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16384819149971008, "target_z": -0.33007813322242874, "ce": 6.133810997009277, "genuineness": 4.3881025314331055, "identity": 0.642288088798523, "hypothesis": "De weg gaat linksaf naar de brug. Loopt verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "436e16ff14448bd255997635097635fe3a468de26eb03d07ffa5a37ebd91aa9d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "529e700636aa67885d55171aef061568ff78b263cd4a41a06afc5e064ecdd1af", "generation_seconds_batch": 16.692012754967436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0563547611236572, "target_z": 3.187500180027914, "ce": 6.149696350097656, "genuineness": 3.9550557136535645, "identity": 0.4169546365737915, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/436e16ff14448bd255997635097635fe3a468de26eb03d07ffa5a37ebd91aa9d.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "43aea32b51424c1f76da7a929d0af4319f3e6f33c72d94763c35a90d8fae87cd", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "77f92bd16ba3602b82e88fb40f31a4bd5fa801e7afc8cc4eb51c7d5fca9e8d7f", "generation_seconds_batch": 26.33212081901729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8966317176818848, "target_z": 2.8906249549930214, "ce": 6.197352409362793, "genuineness": 3.4969046115875244, "identity": 0.33577412366867065, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/43aea32b51424c1f76da7a929d0af4319f3e6f33c72d94763c35a90d8fae87cd.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "43c31a46d0d3dd849f3abeeb54cf9c9a367c48f911368f8edf6a748a89d28112", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9af898a84a21724500d55f275338b0fbe6b624e6358345008506594f56e7c2e0", "generation_seconds_batch": 24.63613225298468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7575551271438599, "target_z": 0.7734375294276398, "ce": 6.038498878479004, "genuineness": 4.2374773025512695, "identity": 0.6409109830856323, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/43c31a46d0d3dd849f3abeeb54cf9c9a367c48f911368f8edf6a748a89d28112.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "87577a4f6876e46c39b42af09e10bfdc7018bdea7169a15aa8bde0cb4866cda7", "generation_seconds_batch": 19.27918820094783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1386287808418274, "target_z": -0.37695313668450403, "ce": 6.173524379730225, "genuineness": 4.432034492492676, "identity": 0.5850316882133484, "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_Teasing/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "43d80cbd6d94a45c5e5ece4b049ec0a9b031733840f08d5a78864367c9c56771", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "fd6c87f2b8cf75c07856ec9058548aefc8cd603d18e460749b3dc416f7e93f4c", "generation_seconds_batch": 24.4132035470102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2665164470672607, "target_z": 3.578125079627731, "ce": 5.879645347595215, "genuineness": 3.9676074981689453, "identity": 0.5014826655387878, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/43d80cbd6d94a45c5e5ece4b049ec0a9b031733840f08d5a78864367c9c56771.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "448d9401b04d379b242ede48c2e20fe36a0b88e627ea82d828ebb8f5374d50b4", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3485a74dae7a9065e3cef0225809f62d1031e41ce9a7930cce9d55b1690b215f", "generation_seconds_batch": 23.287235655006953, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3123821020126343, "target_z": 1.8046874948068872, "ce": 6.125868320465088, "genuineness": 4.005263805389404, "identity": 0.20276613533496857, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/448d9401b04d379b242ede48c2e20fe36a0b88e627ea82d828ebb8f5374d50b4.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "452f287354bc25a2c6543fb055c885e20b0a78e6d215eb52527a144ab341be88", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f90e56e0b5faa029b227d0f73909dd18f31bf7398658eb3fbffb358c243540cd", "generation_seconds_batch": 24.803426358033903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5351535081863403, "target_z": 2.218749923834344, "ce": 6.221180438995361, "genuineness": 4.086852550506592, "identity": 0.49352699518203735, "hypothesis": "Ik 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_Teasing/452f287354bc25a2c6543fb055c885e20b0a78e6d215eb52527a144ab341be88.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "455f96a3465880713388ba23923f383c856f719e1af1eba61b4020723a8fb406", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f6d1ec660b93dea86a6a122eb3151fbfbd667bc61c22b80050b03b5e53833cd6", "generation_seconds_batch": 26.016615148982964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.009749174118042, "target_z": 1.2421874532619839, "ce": 6.38797664642334, "genuineness": 4.13078498840332, "identity": 0.1910608559846878, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/455f96a3465880713388ba23923f383c856f719e1af1eba61b4020723a8fb406.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "45e102d14da8086a01bf13d7961299a04baea039e5cd26b70a84eb9e9db96bd8", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cbd0c288b91cd22e568de3d89130ed532f71d62a5b4e1aaf853c3d0fec1886fc", "generation_seconds_batch": 22.73186831199564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07452946901321411, "target_z": -0.496093726630992, "ce": 6.109982967376709, "genuineness": 4.469690799713135, "identity": 0.6205552220344543, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/45e102d14da8086a01bf13d7961299a04baea039e5cd26b70a84eb9e9db96bd8.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "588b616b1d1626e0e0005e65894e30df5c9311cfe0c47534cfaace3c46639d58", "generation_seconds_batch": 18.128514499985613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4927513003349304, "target_z": 0.28124996537924735, "ce": 6.316492557525635, "genuineness": 4.2751336097717285, "identity": 0.5870914459228516, "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_Teasing/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "4618e00dcba90d3e6e5b58acf1ea5e8993f2fe40554e57afb78c258f9e9fa0a1", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "42fe9081724bf5a05c499af79a81a8f906c20129d4adf95edf021167d03ed9be", "generation_seconds_batch": 17.116788815008476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8882251977920532, "target_z": 2.8749998615169896, "ce": 6.197352409362793, "genuineness": 4.482243061065674, "identity": 0.4902085065841675, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4618e00dcba90d3e6e5b58acf1ea5e8993f2fe40554e57afb78c258f9e9fa0a1.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "46b6131183c17ffe295614ab10ebd0ebd736ff8cb692791e6cd6e205fe2b8ac5", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "89eba873afc5d7cb8971087f366c854cb8479d63661b131929b9d314de4e80dd", "generation_seconds_batch": 18.983435570960864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9382941722869873, "target_z": 1.1093749342205699, "ce": 6.213237762451172, "genuineness": 4.331617832183838, "identity": 0.3699592649936676, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/46b6131183c17ffe295614ab10ebd0ebd736ff8cb692791e6cd6e205fe2b8ac5.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "47446e7aecb8892d928673f16a6f6d6c40ed62be3dd9d16ec0c8230a993ec804", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5de68625832bfdacafea7eaee65c9af1c2af5f2923c59b7716e3759b38857543", "generation_seconds_batch": 22.643289708998054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2244842052459717, "target_z": 3.5000002769660212, "ce": 6.213237762451172, "genuineness": 4.3504462242126465, "identity": 0.6681127548217773, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/47446e7aecb8892d928673f16a6f6d6c40ed62be3dd9d16ec0c8230a993ec804.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "5b0a44f5c6712e9891a83469e362e1a2e2356e16a4bf18096fa17d75d564dac6", "generation_seconds_batch": 19.806637458968908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03670033812522888, "target_z": -0.566406259520707, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.7115380167961121, "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_Teasing/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.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": "47ffea66130519a9c0a3a53ee1ad60796c4f8ab42988b5d077c3bcf88a440ae4", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "768698aa7473a366b9a2874f322bbc3dca42552221eef2d081b512a6ff551193", "generation_seconds_batch": 18.85566410503816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.980696439743042, "target_z": 3.046875003462075, "ce": 6.38003396987915, "genuineness": 4.394378662109375, "identity": 0.5837620496749878, "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_Teasing/47ffea66130519a9c0a3a53ee1ad60796c4f8ab42988b5d077c3bcf88a440ae4.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": "486c909a98ee1fa90ea619b73e83b81d4ce5cee19bbbb15d0c179b583a4e9033", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ebd4fa85dc1a4c5712484f0c5c60fbc60f6c4bfa74cd9262712b1cdfdcb6119f", "generation_seconds_batch": 26.979391054948792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1480860710144043, "target_z": -0.35937498961377423, "ce": 6.1020402908325195, "genuineness": 3.9801597595214844, "identity": 0.4953181743621826, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/486c909a98ee1fa90ea619b73e83b81d4ce5cee19bbbb15d0c179b583a4e9033.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "48afbdafe29cf543e3584bf285971decbe82b9bbb1208324e995db483157995b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "795b97e27b852c8224ca753cbc345c54c1edaa1f867592d4d1581b4fe96a8d46", "generation_seconds_batch": 21.426194777945057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9298877716064453, "target_z": 1.0937500623173548, "ce": 5.879645347595215, "genuineness": 4.005263805389404, "identity": 0.5190393328666687, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/48afbdafe29cf543e3584bf285971decbe82b9bbb1208324e995db483157995b.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": "48c405cc2201908425965d17fa3e9bbbe63be69b3ddaa4e54a8f3d92f11f294b", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d07b276da44cb8e4346cfa4ea10e2f2c050c9497afc34d3283a4f8f2114a53be", "generation_seconds_batch": 24.478578449925408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2619433403015137, "target_z": 1.710937598669145, "ce": 6.268836498260498, "genuineness": 4.124508857727051, "identity": 0.553551435470581, "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_Teasing/48c405cc2201908425965d17fa3e9bbbe63be69b3ddaa4e54a8f3d92f11f294b.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "121f062040eeb192d2daf377e0a8442f1122a9bd5e2c8bbcea422f714121cc75", "generation_seconds_batch": 19.08152521797456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0902915894985199, "target_z": -0.4667968702396465, "ce": 6.125868320465088, "genuineness": 3.9299514293670654, "identity": 0.7087867259979248, "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_Teasing/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "49e110d48e14d4e15232204c902911c2d1ff72978c54edf2afaa39b4b154a318", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "49e89f8541b3c1e81e787512fb1825b150a83197fad997288894d9051916f6d0", "generation_seconds_batch": 24.50199944898486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3165853023529053, "target_z": 1.8124999307584948, "ce": 6.1894097328186035, "genuineness": 4.143336772918701, "identity": 0.7057509422302246, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/49e110d48e14d4e15232204c902911c2d1ff72978c54edf2afaa39b4b154a318.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "4a3137708e2df1e0a4b1ef26343947763d7591b3201d799c4bc8ad468653f7ac", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2d08f406e91b8d14a95ac68d49a9f372fa17d25e5f7fbbe217a1af2ef73f9ccb", "generation_seconds_batch": 22.384759754058905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7873475551605225, "target_z": 2.6874998476686884, "ce": 6.038498878479004, "genuineness": 3.923675537109375, "identity": 0.4371684193611145, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4a3137708e2df1e0a4b1ef26343947763d7591b3201d799c4bc8ad468653f7ac.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "4ad8cb4c7e74f414008a8508225e27ac1a82d376656c9d95bcf7ac0232d926f1", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6a9b6cbea73e373e7999be49da1a00fcf1d91c07e1050dfbfef47f08eb9ea067", "generation_seconds_batch": 23.010283267940395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16384819149971008, "target_z": -0.33007813322242874, "ce": 5.998785495758057, "genuineness": 4.444586753845215, "identity": 0.7816413044929504, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4ad8cb4c7e74f414008a8508225e27ac1a82d376656c9d95bcf7ac0232d926f1.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": "4b018f0d3a8fe4f268185be30e0167ad83ea849e0e1fa26065ae3685f4b1f12e", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fe53dd4461d9af4021f360ac2ac759b60698b04b6b0624ef9f358a1f09b5a0ec", "generation_seconds_batch": 24.47488989494741, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5519664287567139, "target_z": 2.2499998892135915, "ce": 6.173524379730225, "genuineness": 4.017816066741943, "identity": 0.5317623615264893, "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_Teasing/4b018f0d3a8fe4f268185be30e0167ad83ea849e0e1fa26065ae3685f4b1f12e.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "4b722313b13545ea903f225cf4cd1399f16d15229c50b3ce7aa307f0767556c2", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "86f19b46d4d4649e1cdbd7541ecca41bff8aa12871ec8f3c6be7c26e7096602b", "generation_seconds_batch": 21.95834291097708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7995874881744385, "target_z": 0.8515625536621666, "ce": 6.062326908111572, "genuineness": 4.18726921081543, "identity": 0.5877983570098877, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4b722313b13545ea903f225cf4cd1399f16d15229c50b3ce7aa307f0767556c2.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": "4b9c40c81cfec066c4d8ef3cbb695ebd01fbb4a197b97413ccc80bc68854f2ff", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4197b4312daa1c2551d24ecb23ec8f6792019285d8d5c629c5982a25074a96e6", "generation_seconds_batch": 20.86571554397233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.342174768447876, "target_z": 3.7187502561935695, "ce": 6.078212261199951, "genuineness": 4.036643981933594, "identity": 0.6204204559326172, "hypothesis": "De weg gaat linksaf na de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4b9c40c81cfec066c4d8ef3cbb695ebd01fbb4a197b97413ccc80bc68854f2ff.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "4bbc46a9cc2260e2d5e4160a9b8565dad14c2efcdd08a4ac36a1841b634a9700", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5e9246b6e6d69267d869f68ec7886e758184f3cfdb539df8b69c4a24f44d2147", "generation_seconds_batch": 24.876538424985483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5957305431365967, "target_z": 0.4726561972033522, "ce": 6.284721851348877, "genuineness": 4.168440818786621, "identity": 0.48392701148986816, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4bbc46a9cc2260e2d5e4160a9b8565dad14c2efcdd08a4ac36a1841b634a9700.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "4be95bdc67545feff30c917868604e8b24d2d34270adeec68c045a02d732f3cc", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2e6db8ed82a754199f0abbdc37f0033a69cb693224b3869de8d085affce333ab", "generation_seconds_batch": 25.444958592997864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.820973515510559, "target_z": 2.75, "ce": 6.046441555023193, "genuineness": 4.281409740447998, "identity": 0.7469946146011353, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4be95bdc67545feff30c917868604e8b24d2d34270adeec68c045a02d732f3cc.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "4c36a6f7e0fb6f2ac4beabec7a5e7bc163a85b132b6f13a7c0f844383a9fb9ed", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8c7db93a7f013a1f480ff8291c58080293a10d9d2e6ac664071450159a082b37", "generation_seconds_batch": 23.201141300960444, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15544173121452332, "target_z": -0.34570311591205244, "ce": 6.157639026641846, "genuineness": 4.6705241203308105, "identity": 0.6917227506637573, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4c36a6f7e0fb6f2ac4beabec7a5e7bc163a85b132b6f13a7c0f844383a9fb9ed.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "4c7ad432ef31036f7bb6c87af6ad0af3f6ecefaff1577b6b6874efbcca7bd9ad", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "89c1cc50f9dce4df1fb5078eee82fd76c56adf116ca863d6024a1f5e12c86740", "generation_seconds_batch": 23.544822718016803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8966317176818848, "target_z": 2.8906249549930214, "ce": 5.7406487464904785, "genuineness": 4.15588903427124, "identity": 0.5359841585159302, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4c7ad432ef31036f7bb6c87af6ad0af3f6ecefaff1577b6b6874efbcca7bd9ad.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "4c8e197b9cf4ad35b426ac015710c6424a78bfc34581fd469dfa9afc8887737f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "abc62bd252e612f5caac1779f00488e3f5ac6e85ef5eed81ff7ac79ceb812632", "generation_seconds_batch": 24.910614092019387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1656386852264404, "target_z": 3.390624844206613, "ce": 5.804190158843994, "genuineness": 3.9299514293670654, "identity": 0.569574236869812, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4c8e197b9cf4ad35b426ac015710c6424a78bfc34581fd469dfa9afc8887737f.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "4e3bafb9055964614aa763b9900a48df21e9cba5fa9367847451a43944b279b7", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2ed28cfb6864ed7f6de805acbfd27ed1c2fd4b295bebbacb9420b33ab407fba9", "generation_seconds_batch": 25.041427804972045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9382941722869873, "target_z": 1.1093749342205699, "ce": 6.149696350097656, "genuineness": 3.961331605911255, "identity": 0.2427821159362793, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4e3bafb9055964614aa763b9900a48df21e9cba5fa9367847451a43944b279b7.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "4e3d9b63bbe8b5365ee8f310c3036b2adc10c8b395d976ea42d012cd25137228", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4ccc0db576d5526cd6edd0fb57b8c1f1d136d217f3058e0e98c00135583bdde1", "generation_seconds_batch": 25.090835456969216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12076504528522491, "target_z": -0.4101562387482554, "ce": 6.181467056274414, "genuineness": 4.400654315948486, "identity": 0.7049071788787842, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4e3d9b63bbe8b5365ee8f310c3036b2adc10c8b395d976ea42d012cd25137228.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "4ec48254fda5abb9ac2b0826c585e71d972540986d943735950f77c1695aa88f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "95f775d432993d6d2f4a5ead461f8e3d38be7a43d5a6438e70f33ebcf857c7f8", "generation_seconds_batch": 24.202861278085038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4594953060150146, "target_z": 2.0781249688413226, "ce": 6.141753673553467, "genuineness": 3.7918784618377686, "identity": 0.3447006344795227, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4ec48254fda5abb9ac2b0826c585e71d972540986d943735950f77c1695aa88f.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "4f1d6cefe6fe9e2b48cee4e6de3f4455bf8052c58c70a07d275d2dbdd486c55b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2311a5e2f3957a9a91ee851e6d92d49ba5e536434c65982afd0431058aeeecd6", "generation_seconds_batch": 17.319545330945402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20482973754405975, "target_z": -0.25390624567240594, "ce": 6.2767791748046875, "genuineness": 4.061748504638672, "identity": 0.6479421257972717, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4f1d6cefe6fe9e2b48cee4e6de3f4455bf8052c58c70a07d275d2dbdd486c55b.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "4f3999ca643e966512b5c7559dacb5f31663677512ccfe9e25e180f02f36f88d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "764fd95776b07ee7076c83299703f7eae438e66f27d2d6f44725c03468bac7a4", "generation_seconds_batch": 23.737654247903265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.989102840423584, "target_z": 3.0624998753652903, "ce": 6.0146708488464355, "genuineness": 4.068024158477783, "identity": 0.5550392270088196, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4f3999ca643e966512b5c7559dacb5f31663677512ccfe9e25e180f02f36f88d.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "4fbc01836d38a9668c0ae3706934ed2f59067b46bdbed79186997794181ac5e3", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b2df50595ae02a6802198e6449073227375d1a104997fb1f4e5de3bec8e10b5b", "generation_seconds_batch": 23.774357768008485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6780635118484497, "target_z": 2.484374961917172, "ce": 6.229123115539551, "genuineness": 3.9927117824554443, "identity": 0.18395395576953888, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4fbc01836d38a9668c0ae3706934ed2f59067b46bdbed79186997794181ac5e3.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "4fd57f87cc9633d8d203a6c5c9bc696a519c94686e6abc7642af450e89f1b793", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6899c91e02504117167d8a53a7f137bf3e8b417b13ea878de4be821ce17e7699", "generation_seconds_batch": 25.38431250897702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3964468240737915, "target_z": 1.9609375432759408, "ce": 6.284721851348877, "genuineness": 4.030367851257324, "identity": 0.1710367202758789, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4fd57f87cc9633d8d203a6c5c9bc696a519c94686e6abc7642af450e89f1b793.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "4fdbc0c02467daa228d9fd4cd35656baea53ef8bd06db8d87979fa30e7281da0", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "285399a0b28c0910be82f3a29f937f952b3f8d3aaf60e5a673d6e965e799624c", "generation_seconds_batch": 23.939425475895405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8332133293151855, "target_z": 0.9140624844206613, "ce": 6.268836498260498, "genuineness": 4.570107460021973, "identity": 0.5516829490661621, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4fdbc0c02467daa228d9fd4cd35656baea53ef8bd06db8d87979fa30e7281da0.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "4fddf1a927c827b2b1eeed471da5e8af2c6c7a87820f7ba7554345ca7f30295e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "89b842b7f6d1b1ad0ce104d67adb3be81b57de0476365e95b9c76e45b1eeac89", "generation_seconds_batch": 14.934474849957041, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.83111172914505, "target_z": 0.9101562664448575, "ce": 6.268836498260498, "genuineness": 4.394378662109375, "identity": 0.505790114402771, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/4fddf1a927c827b2b1eeed471da5e8af2c6c7a87820f7ba7554345ca7f30295e.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "5011dc45aec2ea4207635655983929b14452fd8122c19fc3b047fa7af9f8510d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2e41d26ce6177dee761aaaf03e331f1ec60e4e8ba13a8ff7d561272a706144bc", "generation_seconds_batch": 23.666363507974893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3502111434936523, "target_z": 1.8749998615169894, "ce": 6.181467056274414, "genuineness": 3.8044304847717285, "identity": 0.3056217432022095, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/5011dc45aec2ea4207635655983929b14452fd8122c19fc3b047fa7af9f8510d.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "5041a5b63f7ab8daf7d1612e3fbe58740f0bc3847295ce6f0e18496fe54f17f0", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8c28217000b88b7d9ccb09a6c654f3b15f669737aa5935c866b95552e6c07d14", "generation_seconds_batch": 23.99511252704542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2160775661468506, "target_z": 3.484374961917172, "ce": 6.205295085906982, "genuineness": 3.9048471450805664, "identity": 0.4733767807483673, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/5041a5b63f7ab8daf7d1612e3fbe58740f0bc3847295ce6f0e18496fe54f17f0.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "507f40d1e77a27435038c5447575c4f11f4cd0a71d345c4add3ea563966cc355", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "293905bdf2ef295801565e5828636cee8b4fcad599c3fbb10cb6db16f9504001", "generation_seconds_batch": 24.99491029290948, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36665427684783936, "target_z": 0.046875003462075265, "ce": 6.133810997009277, "genuineness": 4.256305694580078, "identity": 0.5995082855224609, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/507f40d1e77a27435038c5447575c4f11f4cd0a71d345c4add3ea563966cc355.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": "509edf5ec8b23941f7bfa5390d291050a5d19ac9b95fcc67d2309d5f9c508c35", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1f53ad91c1605b791241d63d88fef26e63849f2266218726f23fe7112a5e9b71", "generation_seconds_batch": 28.62437602400314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.989102840423584, "target_z": 3.0624998753652903, "ce": 6.23706579208374, "genuineness": 4.055472373962402, "identity": 0.46207502484321594, "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_Teasing/509edf5ec8b23941f7bfa5390d291050a5d19ac9b95fcc67d2309d5f9c508c35.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "50b35e357b1f33c267db65bbbe9bde085b37cfda205b0a884362e5d7e5ed9e08", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2a06d3438f9d9ec30b0b2f84d38f1b2f127dfe32dc2d6435077048f373b32af8", "generation_seconds_batch": 18.465325520024635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5183405876159668, "target_z": 2.187499958455097, "ce": 6.221180438995361, "genuineness": 3.9927117824554443, "identity": 0.45832353830337524, "hypothesis": "The 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_Teasing/50b35e357b1f33c267db65bbbe9bde085b37cfda205b0a884362e5d7e5ed9e08.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "50f7ce3d2718361321428323e57dda8930b60227db47276973a801d89db7dfa3", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ef2e5919a430250fb29aba8c83fb9428ef690c169a9e31da14cbcd34d1ef66e5", "generation_seconds_batch": 23.06217030901462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.377162367105484, "target_z": 0.06640625952070697, "ce": 6.268836498260498, "genuineness": 4.256305694580078, "identity": 0.45706403255462646, "hypothesis": "J'ai trouvé la 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_Teasing/50f7ce3d2718361321428323e57dda8930b60227db47276973a801d89db7dfa3.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "51983bf8b4b07214538709a921d0a99a92368633db60cbaf7a63c94467a8616f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e88072667a1d28a641f488e1cddb3882e7705ca15099bcf9a91d80c8cb1c6f79", "generation_seconds_batch": 23.287235655006953, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.577185869216919, "target_z": 2.296874948068871, "ce": 6.1020402908325195, "genuineness": 3.9927117824554443, "identity": 0.5586224794387817, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/51983bf8b4b07214538709a921d0a99a92368633db60cbaf7a63c94467a8616f.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "51aada9db63898639d4b355812091ee9a5fbf32f7c7adefe9aaa264a0ed635ba", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a65371f91ac864dacf0fbdf72d07151be56255a53309ba462cd048b55880df74", "generation_seconds_batch": 24.50199944898486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9677168130874634, "target_z": 1.164062429027457, "ce": 6.1894097328186035, "genuineness": 3.9048471450805664, "identity": 0.7107329368591309, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/51aada9db63898639d4b355812091ee9a5fbf32f7c7adefe9aaa264a0ed635ba.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "5216c1cce81f1860915d297e95d57dda7d2ab33fd28b35dc00bc86fbc6c14626", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "39086c9c5958e869ebf6f977c86f9495f68600ab1bcdb41356b70523a2a7def3", "generation_seconds_batch": 17.116788815008476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2665164470672607, "target_z": 3.578125079627731, "ce": 6.165581703186035, "genuineness": 4.1998209953308105, "identity": 0.6440911293029785, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/5216c1cce81f1860915d297e95d57dda7d2ab33fd28b35dc00bc86fbc6c14626.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "5249b1cfc07d2b5d6385f8cd0c76ed8dfa0cd19e2d05731b1fa4130ed0fee62e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "78d53ec6c8a7e081f0bd6fc87d2ed7612750ba88e1f05a08bd27423168ff58da", "generation_seconds_batch": 25.095852859085426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29204684495925903, "target_z": -0.09179689793624862, "ce": 6.316492557525635, "genuineness": 4.507347106933594, "identity": 0.705930233001709, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/5249b1cfc07d2b5d6385f8cd0c76ed8dfa0cd19e2d05731b1fa4130ed0fee62e.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "5287c01fb39c571af7e3c8d683850e33eb8f07b4078d7368a782749e2acaa3d7", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d5bc37cfd21dc84efad87b16aa5dcc251e6f10e659baa25cb1fbee79bb6b298a", "generation_seconds_batch": 25.47528666688595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5831208825111389, "target_z": 0.44921877856212095, "ce": 6.117925643920898, "genuineness": 4.105680465698242, "identity": 0.5973434448242188, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/5287c01fb39c571af7e3c8d683850e33eb8f07b4078d7368a782749e2acaa3d7.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "52f6530768dd43208cc20777e960d9c5991c78c9411e80027fb2c527a6a69cd2", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ae59f4c46c5b3c36168e20765e3128951d369f586133d6ab225c61660b60fdbb", "generation_seconds_batch": 22.26513466099277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6864699125289917, "target_z": 2.4999998338203873, "ce": 5.982900142669678, "genuineness": 3.575355052947998, "identity": 0.2511742413043976, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hin.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/52f6530768dd43208cc20777e960d9c5991c78c9411e80027fb2c527a6a69cd2.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "532760784dc8d5e640fccc97d32113b9f634b0feb70f873e162c71ddc355f0c6", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "eea440632a2677373491a1b2fafb47ae43333dd4b4af4e244cf1e6732ff671cf", "generation_seconds_batch": 24.846673545078374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.005915880203247, "target_z": 3.093750062317355, "ce": 5.8875885009765625, "genuineness": 4.111956596374512, "identity": 0.6050523519515991, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/532760784dc8d5e640fccc97d32113b9f634b0feb70f873e162c71ddc355f0c6.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "53b698ed6c6253ee8192d730f10c05278350cadf1da821860ac6c915e42e895d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "01be606ed5f06446f2037ff22a04c80ce285596c770a1f28078ef452b7a15c9b", "generation_seconds_batch": 25.899446246097796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6945065855979919, "target_z": 0.6562499930758495, "ce": 6.348263263702393, "genuineness": 4.137060642242432, "identity": 0.5795854330062866, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/53b698ed6c6253ee8192d730f10c05278350cadf1da821860ac6c915e42e895d.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "541abeeb26a8b76c63915cba3da005b06bac0a434dc23bfeca82b64e05be85b9", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "518d644b767039e157f245e9fe8ac1dceb577fa3032f2853b136beb07304c4db", "generation_seconds_batch": 22.765621350961737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5603729486465454, "target_z": 2.2656249826896238, "ce": 6.316492557525635, "genuineness": 4.356721878051758, "identity": 0.6084412336349487, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/541abeeb26a8b76c63915cba3da005b06bac0a434dc23bfeca82b64e05be85b9.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "541d5f68fb498f572883f165604b6f67f7949a3107ec56519b5bc4d7273e61b6", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "527537e9e0fa31854bb2c61c7d217ead2b40a4a6e09c0447724b62904362d1bb", "generation_seconds_batch": 25.34324284410104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.224114179611206, "target_z": 1.6406250103862259, "ce": 6.149696350097656, "genuineness": 4.162164688110352, "identity": 0.6011443734169006, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/541d5f68fb498f572883f165604b6f67f7949a3107ec56519b5bc4d7273e61b6.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "105161afce284b468b183fc9684d7b2d60fa1c0a6481b9ae01356f9a11ffa985", "generation_seconds_batch": 18.128514499985613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13127312064170837, "target_z": -0.39062501038622577, "ce": 6.300607204437256, "genuineness": 3.9425034523010254, "identity": 0.4822678864002228, "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_Teasing/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "54eb165a140719dce57b994a882ea435c295b157f4cbba0fa8976feab73fe3fa", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a1dd1e67a249a29b84d21bf727aa06092351b8bd22cba5403f378b3ed45d3dab", "generation_seconds_batch": 25.35419981100131, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5687793493270874, "target_z": 2.281249854592839, "ce": 6.0146708488464355, "genuineness": 4.105680465698242, "identity": 0.5640616416931152, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/54eb165a140719dce57b994a882ea435c295b157f4cbba0fa8976feab73fe3fa.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "555b14a7b9fa16bbfde9884ae0623956973718b47539314b197bf4c8f8f6b532", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "559af19adbd66087fe7e8736f76e6beaf0b6f70a05dbc154cb1e2959ad59d9cf", "generation_seconds_batch": 25.58080070198048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9975093603134155, "target_z": 3.0781249688413226, "ce": 6.260893821716309, "genuineness": 3.9048471450805664, "identity": 0.4594344198703766, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/555b14a7b9fa16bbfde9884ae0623956973718b47539314b197bf4c8f8f6b532.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "55a1df646c2159038d633233a3bfeebb85db2737b53ff4986659d570843ae84e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "5752d2913e3b7c8c3746065e365a4eb979127bf87b5c25a001a46d27dc0ba330", "generation_seconds_batch": 26.51808729104232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.820973515510559, "target_z": 2.75, "ce": 6.23706579208374, "genuineness": 3.747946262359619, "identity": 0.2555896043777466, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/55a1df646c2159038d633233a3bfeebb85db2737b53ff4986659d570843ae84e.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "55b264027abb8b96f2a451a02148f464eee10aeceecc7fa468980581d6df5f84", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "bf4aaa2dcead77e12bd0a1c23c3299e54a10eabab840d55ad589e220da6a2140", "generation_seconds_batch": 15.625592457014136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2412970066070557, "target_z": 3.5312500207724518, "ce": 6.070269584655762, "genuineness": 3.911123275756836, "identity": 0.5909466743469238, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/55b264027abb8b96f2a451a02148f464eee10aeceecc7fa468980581d6df5f84.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "568ceb28669fd142845f3dbc97cadaee30c14e361f7abdda0afcbd8b8fab1b7d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6bda7422de7bc60d5e5f5f00b86ddcc9e28c30665162fade75a3eaf16fb1f49c", "generation_seconds_batch": 15.92507423600182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.723929226398468, "target_z": 0.7109374878827366, "ce": 6.260893821716309, "genuineness": 4.281409740447998, "identity": 0.5187458992004395, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/568ceb28669fd142845f3dbc97cadaee30c14e361f7abdda0afcbd8b8fab1b7d.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "56e600be73e44ad1e151c6fc071d877b7845dcc8040355824539ea2024830040", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e1418220729f3e66b822a2c3ac7b3afa58909c83a8cb37a3d153fd827267e3b2", "generation_seconds_batch": 25.85165354399942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0770009756088257, "target_z": 1.3671875363517902, "ce": 6.3641486167907715, "genuineness": 4.137060642242432, "identity": 0.25040674209594727, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/56e600be73e44ad1e151c6fc071d877b7845dcc8040355824539ea2024830040.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": "56ea1c792b385be45825648dbc1fc9db2251dba0e718fbe5c9a852c61617376d", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e155debbf73adaccaf12d9a2848bc85c4302760bc7e1890c23281cd46d6417ed", "generation_seconds_batch": 24.039263216080144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.413259744644165, "target_z": 1.9921875086551881, "ce": 6.181467056274414, "genuineness": 3.9173994064331055, "identity": 0.42631328105926514, "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_Teasing/56ea1c792b385be45825648dbc1fc9db2251dba0e718fbe5c9a852c61617376d.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": "56f53f734a9b559a6581d96be667e02f3ebe9f2cc336521ae34675e1bdffb864", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "778cc7439202968919ce05c018da1643d9336ffab26006bcaafc05c7acf121cf", "generation_seconds_batch": 17.622418954968452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.198894739151001, "target_z": 1.5937499515309463, "ce": 6.332377910614014, "genuineness": 4.413206577301025, "identity": 0.39140141010284424, "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_Teasing/56f53f734a9b559a6581d96be667e02f3ebe9f2cc336521ae34675e1bdffb864.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "5700128be58e9fb0ccd9d2f6f3fecc7115f00a5ae2c97f332215645079fee580", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6f4b583591557e1d267c02586ba4417a642c81a6f67cc27cb499f4155e7ecda5", "generation_seconds_batch": 16.33112779504154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1740453243255615, "target_z": 3.406250159255462, "ce": 6.1894097328186035, "genuineness": 3.948779582977295, "identity": 0.45432406663894653, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/5700128be58e9fb0ccd9d2f6f3fecc7115f00a5ae2c97f332215645079fee580.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "57ee91ccbbe945a38a1fdb3860bfddae13cd0c15ee1aabab5ec9441dd08b0b6e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0a2cfd03730bbff5161429258d488d84fd4746cdf48882f6925979c98c64d3e3", "generation_seconds_batch": 23.60380029294174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08293592929840088, "target_z": -0.4804687439413683, "ce": 6.109982967376709, "genuineness": 3.7793264389038086, "identity": 0.3776741027832031, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/57ee91ccbbe945a38a1fdb3860bfddae13cd0c15ee1aabab5ec9441dd08b0b6e.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "58000b3d3751e9d720b81d49ad009faa3bf27052f61f207089dc2de048d69b75", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "df3d0cad49a57b15f715c239c5d79c32f9f16dfcb183e605ea36a4144151352b", "generation_seconds_batch": 24.50435350195039, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5439300537109375, "target_z": 4.093750283890172, "ce": 6.181467056274414, "genuineness": 4.13078498840332, "identity": 0.4164654612541199, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "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_Teasing/58000b3d3751e9d720b81d49ad009faa3bf27052f61f207089dc2de048d69b75.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "58010943782cdbcac831ae48c332ee1a6e07055fad9a4c7a023aa9334ccd323a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a5739a2ccc213ffb55fd30a4996ee6a6474184d79b399ec0ccbe0ffeffcbbef3", "generation_seconds_batch": 17.57026849698741, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.695246458053589, "target_z": 4.375000193876215, "ce": 6.117925643920898, "genuineness": 4.337893962860107, "identity": 0.43460333347320557, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/58010943782cdbcac831ae48c332ee1a6e07055fad9a4c7a023aa9334ccd323a.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "586fe9b231293b045bf140ae1dc9f0a0bb99f9c4ec8a0bfda304d7f0627febb3", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "354f47e554e81b7bc617b04d6501954f03962b1d244691ea7b61b0e30428bbd5", "generation_seconds_batch": 23.424945867969655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0899806022644043, "target_z": 3.2500001107864085, "ce": 6.086154937744141, "genuineness": 4.111956596374512, "identity": 0.41149789094924927, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/586fe9b231293b045bf140ae1dc9f0a0bb99f9c4ec8a0bfda304d7f0627febb3.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "58ac98bdda4e13b1db6d2163e83803f6df574ff8b8bfec3af0f2549a75c1aad5", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "942f76ff75eb05ec32b9ed19256c540fe370273e588fb2b43509e08ad21c6dd0", "generation_seconds_batch": 24.01766341191251, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5775558948516846, "target_z": 4.156250214648666, "ce": 6.197352409362793, "genuineness": 4.118232727050781, "identity": 0.42283058166503906, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/58ac98bdda4e13b1db6d2163e83803f6df574ff8b8bfec3af0f2549a75c1aad5.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "58b3ad7c86b5beeb1d9314ad3c14fd01b507004090f05db570255d1450c58770", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "96c7ea33432ee839d7a59ac6dee091685278e81c741941acc141fb2c6a1eeea5", "generation_seconds_batch": 23.091123237041757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8545993566513062, "target_z": 2.8124999307584946, "ce": 6.229123115539551, "genuineness": 3.616149425506592, "identity": 0.4954955279827118, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/58b3ad7c86b5beeb1d9314ad3c14fd01b507004090f05db570255d1450c58770.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": "5a07f981ae811b4565499c514734f7500fcbe748eb33cc51a525c8475ac5e3e3", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "48fd60f7aab0100c7432ae79449ca3e0753e99e8df8b2c2fea65f92207e061c3", "generation_seconds_batch": 25.22583017195575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1022204160690308, "target_z": 1.4140625952070698, "ce": 6.213237762451172, "genuineness": 3.9048471450805664, "identity": 0.3571598529815674, "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_Teasing/5a07f981ae811b4565499c514734f7500fcbe748eb33cc51a525c8475ac5e3e3.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "5b0881012c2ba57d41ac0961690e5a7536a26b4013dfa6e5ba4c933cabc23d2d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d6a8093a111de988efc1284022e075fe0c6e061fb669c2108ab76944ed108691", "generation_seconds_batch": 23.20555297099054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.820973515510559, "target_z": 2.75, "ce": 6.2767791748046875, "genuineness": 4.1998209953308105, "identity": 0.49428486824035645, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/5b0881012c2ba57d41ac0961690e5a7536a26b4013dfa6e5ba4c933cabc23d2d.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "5bbaa878045d7c9fce4a589b29e76192b5de345dadb34da794b6bf9a85cc5195", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b4140ca2bda8fb20ea624785f5c74a3c50f086a20b4c42e377dc5af4171e783f", "generation_seconds_batch": 23.607628048048355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7260308265686035, "target_z": 0.7148437058585404, "ce": 6.507116317749023, "genuineness": 4.168440818786621, "identity": 0.6779975295066833, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/5bbaa878045d7c9fce4a589b29e76192b5de345dadb34da794b6bf9a85cc5195.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "5bc4356a19913468b2398bea7044704afeb6734025f314cb250079af281be7c1", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a380eaa2947fe49dff09619b76d7264755747e602b6a41d7801ae2d5da88b13e", "generation_seconds_batch": 17.146719772019424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9298877716064453, "target_z": 1.0937500623173548, "ce": 6.332377910614014, "genuineness": 3.7416701316833496, "identity": 0.42067331075668335, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/5bc4356a19913468b2398bea7044704afeb6734025f314cb250079af281be7c1.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "5bc9a2def40c5645a45b060ec2d31b71c904f50722f90fe52b11cb1f99f300e1", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "30947ecbf3ae5d88471a576a2bc86cd55c0c6a1662c2d621bb343c388a086829", "generation_seconds_batch": 23.31615127902478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7873475551605225, "target_z": 2.6874998476686884, "ce": 6.054384231567383, "genuineness": 4.105680465698242, "identity": 0.4607601761817932, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/5bc9a2def40c5645a45b060ec2d31b71c904f50722f90fe52b11cb1f99f300e1.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "5c307efb2c14f92491987fbacae2dbe5f9a8e4327d73592a5948be578ece4175", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6b85f6008ccaa6932352fd1979fd26fab36c688710e658f67abe01a446e8accd", "generation_seconds_batch": 16.83157135604415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3586176633834839, "target_z": 1.8906249549930216, "ce": 6.348263263702393, "genuineness": 3.8169827461242676, "identity": 0.29976171255111694, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/5c307efb2c14f92491987fbacae2dbe5f9a8e4327d73592a5948be578ece4175.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "5c5503d2efa7055b597bcb9f173adca2e881efc97092c4f1770cd4eca8fc6945", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "486214294d40422741ff4058b6727cf053535e1ad9c5a972ccf716a027c09663", "generation_seconds_batch": 23.25451606407296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5242756009101868, "target_z": 0.3398437889483467, "ce": 6.300607204437256, "genuineness": 4.2751336097717285, "identity": 0.3737931549549103, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/5c5503d2efa7055b597bcb9f173adca2e881efc97092c4f1770cd4eca8fc6945.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "5da75cf392a9e92a8963dcc35a5e3ba6f03139acbe0500623ff52c4713c047b4", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4c69460859d8e214aabfa777e460bc988142d2f60140b6cb53a9b5d61d1ab1e5", "generation_seconds_batch": 18.983435570960864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8962618112564087, "target_z": 1.031249909986043, "ce": 6.268836498260498, "genuineness": 4.017816066741943, "identity": 0.33606570959091187, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/5da75cf392a9e92a8963dcc35a5e3ba6f03139acbe0500623ff52c4713c047b4.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "9c6cd05c962148188b8389a1c71a1a4de8596beb84756b82607947ca30e95c7d", "generation_seconds_batch": 18.387009910074994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09344401955604553, "target_z": -0.4609374878827366, "ce": 6.252951145172119, "genuineness": 4.557555198669434, "identity": 0.8984833359718323, "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_Teasing/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "5e204686dcf0f31ad492aee20713027802135774e9d7422a90761055abd84a9a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d112c9dbe6e026cfc273e6cfe35a2cf3e0471ca30e8a7b48b330355b6368a468", "generation_seconds_batch": 22.10513888206333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2451303005218506, "target_z": 1.6796874117170808, "ce": 6.395919322967529, "genuineness": 4.193545341491699, "identity": 0.25240105390548706, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/5e204686dcf0f31ad492aee20713027802135774e9d7422a90761055abd84a9a.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "5f1276ba66f603bf363c4e1de98b4fac10b9f6ccf4a17871b1029dd57692ee13", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8a997304c40dabd02a8877a4481b49cd762030050756a1fbdaf36c052500bce9", "generation_seconds_batch": 17.451455220929347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9975093603134155, "target_z": 3.0781249688413226, "ce": 5.998785495758057, "genuineness": 3.7416701316833496, "identity": 0.45627856254577637, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/5f1276ba66f603bf363c4e1de98b4fac10b9f6ccf4a17871b1029dd57692ee13.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "5fdd949ce145238fccece34231f50bce070cae7bac17dbf7277b65079b01fa28", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6d10081496b9890c099163f7fea8f65f7610028d75e2abc9db74060acf6e9924", "generation_seconds_batch": 23.594159456901252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0223588943481445, "target_z": 1.2656249826896238, "ce": 6.38003396987915, "genuineness": 4.105680465698242, "identity": 0.6060894131660461, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/5fdd949ce145238fccece34231f50bce070cae7bac17dbf7277b65079b01fa28.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "606ed4b2aa2b4d423dd97f0a79674a8e902e166141a541ab2fa7803f9ef8b2bd", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "23d79178a717b3827790612989ab12943e8bc87885eced0e8cba5ebb81b14094", "generation_seconds_batch": 26.177133386954665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.030765414237976, "target_z": 1.2812500761656558, "ce": 6.181467056274414, "genuineness": 4.2374773025512695, "identity": 0.7004565000534058, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/606ed4b2aa2b4d423dd97f0a79674a8e902e166141a541ab2fa7803f9ef8b2bd.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "60b1c7baaf6a93c752043b5af4cc56ad788c776ba6108e5cadcfc5873c041494", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3577d7576974d6787614f19170b118c19361479d46af09995ea433bc810301f8", "generation_seconds_batch": 24.962993282009847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2076711654663086, "target_z": 3.4687500900139567, "ce": 6.133810997009277, "genuineness": 4.256305694580078, "identity": 0.5745012760162354, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/60b1c7baaf6a93c752043b5af4cc56ad788c776ba6108e5cadcfc5873c041494.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "60eb9f10e3b8a0c2510d7787a36eda83ded930f895677f49cadb8a18f749e12b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9157bb3ce48a8f142e974625c1260b8ed2203fd15dce736dab922c0a6a527734", "generation_seconds_batch": 16.83157135604415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7200958728790283, "target_z": 2.562499986151699, "ce": 6.165581703186035, "genuineness": 3.6287014484405518, "identity": 0.3812788128852844, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/60eb9f10e3b8a0c2510d7787a36eda83ded930f895677f49cadb8a18f749e12b.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": "614064548d54cb165ba225374b94d24d46dbbfd5fe8063f7444ab1036c969c80", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c851378586357a120aa217822b1f7e99c7f80f54698f13eebbac592db48405a6", "generation_seconds_batch": 17.631409064983018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2661465406417847, "target_z": 1.7187500346207527, "ce": 6.316492557525635, "genuineness": 4.231201171875, "identity": 0.4400062561035156, "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_Teasing/614064548d54cb165ba225374b94d24d46dbbfd5fe8063f7444ab1036c969c80.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "618fed995d83fd6e0859679b508c8252f97bc522becca5ec16efd461fbcb020c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9e9ee5735a180c0806f0d8eb7746eb6902f009549f3f48ca84fdfd597caa4798", "generation_seconds_batch": 24.935827763052657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9722899198532104, "target_z": 3.0312499099860433, "ce": 6.229123115539551, "genuineness": 3.5722172260284424, "identity": 0.1544518619775772, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/618fed995d83fd6e0859679b508c8252f97bc522becca5ec16efd461fbcb020c.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "623b9e5bd6bbac999aad913fcfcdf9f41d5e0d1c3d4a50685551cf97e29d9cb6", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9933a454258dccf07432803a31dc43c0d97046203ce5cccecd5f4b30c395eb45", "generation_seconds_batch": 26.03753468603827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6780635118484497, "target_z": 2.484374961917172, "ce": 6.006728172302246, "genuineness": 3.8169827461242676, "identity": 0.5914844274520874, "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_Teasing/623b9e5bd6bbac999aad913fcfcdf9f41d5e0d1c3d4a50685551cf97e29d9cb6.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "627831fb3164dc18154efe42760e077d85aa7d494480604e9153320c097b7dc6", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4b90e5382ae3aee27add382163167014a52f13418b10637ac8b9254adddf56b0", "generation_seconds_batch": 24.5974917790154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9638835191726685, "target_z": 3.015625038082828, "ce": 5.990842819213867, "genuineness": 4.231201171875, "identity": 0.5132482051849365, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/627831fb3164dc18154efe42760e077d85aa7d494480604e9153320c097b7dc6.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "62d99253f9026b7711a2a77de930ee27239d2ed46ec696ebec0012f4f08daa6e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "74751a3980275087c6bc98c08a7e8a884decc8d25b5fc3bebe1397e37ce7fedc", "generation_seconds_batch": 25.74262660194654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8714122772216797, "target_z": 2.843749896137742, "ce": 6.0146708488464355, "genuineness": 4.174716949462891, "identity": 0.7075461149215698, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/62d99253f9026b7711a2a77de930ee27239d2ed46ec696ebec0012f4f08daa6e.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "62e6cd4184a7ff9fb8dcfc79a680c656386482a9d3aa22bd737ee7a3742a5531", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ccaf2a74c91dac30de97578aec1abf5194bf56db395d78ff57a4a13d7a7c281b", "generation_seconds_batch": 24.739486913895234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12076504528522491, "target_z": -0.4101562387482554, "ce": 6.141753673553467, "genuineness": 4.457139015197754, "identity": 0.7451376914978027, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/62e6cd4184a7ff9fb8dcfc79a680c656386482a9d3aa22bd737ee7a3742a5531.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "62ec050361a59b3e122c5fcb61ca0e50860bdc910fda70899b8cf2f6f0f27dac", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "92eeb870eabc5ca1d078b498665664d4b714f47c8fb4954c87b46ca1fb691edc", "generation_seconds_batch": 16.80015004402958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0223588943481445, "target_z": 1.2656249826896238, "ce": 6.348263263702393, "genuineness": 4.356721878051758, "identity": 0.38913053274154663, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/62ec050361a59b3e122c5fcb61ca0e50860bdc910fda70899b8cf2f6f0f27dac.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "630282300f6ba40761c515a2b8f0e78951e2dfe3e7e336c12f318e5172324a97", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f2d016e20f00360978fa52f606c6eb731771788e84ebfbea7aff6852b434bb5e", "generation_seconds_batch": 23.394666980020702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4039579927921295, "target_z": 0.11621095416123721, "ce": 6.221180438995361, "genuineness": 4.413206577301025, "identity": 0.7737300395965576, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/630282300f6ba40761c515a2b8f0e78951e2dfe3e7e336c12f318e5172324a97.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "6398e6ece2641a41a3c7c9e90e25903726a1a501e53bc4cf0c495a37edb5a9dc", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5c4a889ee0834301656ba9a1fd65131b03127b244308d88388dde0d0d4db7582", "generation_seconds_batch": 16.18058248597663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6839984655380249, "target_z": 0.6367186816240136, "ce": 6.1020402908325195, "genuineness": 3.7918784618377686, "identity": 0.47796952724456787, "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_Teasing/6398e6ece2641a41a3c7c9e90e25903726a1a501e53bc4cf0c495a37edb5a9dc.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "64202d2d4d127221c3fb0d39ace2b550f4ed91cff66a64883dfec76debf9ef25", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0238415e9c22c766fa70556be8b438c57b3eca9d651bb452a717ae1448516a75", "generation_seconds_batch": 23.21062255895231, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1862850189208984, "target_z": 1.5703124221033065, "ce": 6.300607204437256, "genuineness": 3.9425034523010254, "identity": 0.5101000666618347, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/64202d2d4d127221c3fb0d39ace2b550f4ed91cff66a64883dfec76debf9ef25.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "65135bc9cf029408d5ae93a96f787bc64694f200ac921fc71860f4c8b9ddeabb", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4039c55787ff81275284d9dca5773989f9e3111c64d44d13fd53f6187da844e6", "generation_seconds_batch": 23.46814400900621, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8966317176818848, "target_z": 2.8906249549930214, "ce": 6.086154937744141, "genuineness": 4.20609712600708, "identity": 0.5974411964416504, "hypothesis": "Oh, she trouble the petite boat. Elle était pretty de la vie fenêtre. We've got ensemble the contigua.", "wer": 0.6842105263157895, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/65135bc9cf029408d5ae93a96f787bc64694f200ac921fc71860f4c8b9ddeabb.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "6597c0808dcd3fb1cd63c2662ab3f9b5613c5dbe0f2f90196a89d48a7cb670de", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "35c8851e480fe91358273e30637f5100822f854fc240a1c86adc02f9af5be380", "generation_seconds_batch": 16.39244113897439, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6755920648574829, "target_z": 0.6210938097207983, "ce": 6.046441555023193, "genuineness": 4.356721878051758, "identity": 0.6957113146781921, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/6597c0808dcd3fb1cd63c2662ab3f9b5613c5dbe0f2f90196a89d48a7cb670de.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": "65a76d47ad054673043028193be9d221bd2ede49afa28e3755d26a06e3cd6dd6", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5c74e97411498df293e16c2b6f902359324cb307e0daff679fa41acde16b44d8", "generation_seconds_batch": 22.235955324023962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9134446382522583, "target_z": 2.921874920372269, "ce": 6.046441555023193, "genuineness": 3.9676074981689453, "identity": 0.5535238981246948, "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_Teasing/65a76d47ad054673043028193be9d221bd2ede49afa28e3755d26a06e3cd6dd6.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "663d594085aa86db605ef151c207c2f1fc15caad33e5aff812ef7cf36935e648", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c93926747a54f111f1fac7cae75db5fb64703f08f78d10a3bad1c4842fb3531c", "generation_seconds_batch": 23.22472648101393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12917150557041168, "target_z": -0.3945312560586317, "ce": 6.252951145172119, "genuineness": 4.432034492492676, "identity": 0.6509276032447815, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/663d594085aa86db605ef151c207c2f1fc15caad33e5aff812ef7cf36935e648.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "669c9483b1c89045fa93b41dd7d28fec7265634175346272c37e046c5a2c4ed4", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5dba4e47cdd35561262727e2cb3e249729c19140c2728c902046165e2d3953fc", "generation_seconds_batch": 23.20555297099054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.300142288208008, "target_z": 3.6406250103862257, "ce": 6.24500846862793, "genuineness": 4.18099308013916, "identity": 0.4899347424507141, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/669c9483b1c89045fa93b41dd7d28fec7265634175346272c37e046c5a2c4ed4.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "67410c5d50c9a08ff138ef6582313f19ffdac0bd6d26db04a46f531816ab8efe", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1ce099ed52ae3c6a90ed51790badb27326bd7a76bca7a8e2cd8e44b334f70f09", "generation_seconds_batch": 23.010283267940395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6966081857681274, "target_z": 0.6601562110516532, "ce": 6.1020402908325195, "genuineness": 4.3504462242126465, "identity": 0.4000551104545593, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/67410c5d50c9a08ff138ef6582313f19ffdac0bd6d26db04a46f531816ab8efe.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "67584d0b7668cf17cdbc274de66a93e83f7386468216f045f7eda2ac5d6c9bbf", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f9b94aeae3260edc7cae7af5020c46bd327e34c96cee7a7ee75c4c5d7c7bf340", "generation_seconds_batch": 25.444958592997864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4763082265853882, "target_z": 2.10937493422057, "ce": 6.1020402908325195, "genuineness": 4.118232727050781, "identity": 0.6545923948287964, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/67584d0b7668cf17cdbc274de66a93e83f7386468216f045f7eda2ac5d6c9bbf.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "67e78e8f225eda1f15d0e1517b1135b3ee753ebdc3be82037c062802f97a153b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bb47484ddd58c4ea5f7eb45c1ad80574deb6d44c158e3a707912bd5ad91a120f", "generation_seconds_batch": 24.849846267024986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9340909719467163, "target_z": 1.1015624982689625, "ce": 6.308549880981445, "genuineness": 4.2751336097717285, "identity": 0.4131338596343994, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/67e78e8f225eda1f15d0e1517b1135b3ee753ebdc3be82037c062802f97a153b.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "684ab771569d60892754d8dd3d5132b9ed76cfac9a79bfaf8886e21cc167113e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0b5811405520f72e061c9f1451aaa8786151422e1450d79f8d5fbd5e34739aeb", "generation_seconds_batch": 25.604592517018318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2412970066070557, "target_z": 3.5312500207724518, "ce": 6.332377910614014, "genuineness": 4.507347106933594, "identity": 0.6916406154632568, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/684ab771569d60892754d8dd3d5132b9ed76cfac9a79bfaf8886e21cc167113e.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "6889b187297cdeb1c3bde0d52a2728aaf5b82ff9a2f0b633637bb0918eaace09", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "612e40b7673cd437b48f734f7bfe31d020564fd5a101a23e73ba5ab91c948bb4", "generation_seconds_batch": 24.756885462091304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9722899198532104, "target_z": 3.0312499099860433, "ce": 6.038498878479004, "genuineness": 3.936227321624756, "identity": 0.41329342126846313, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/6889b187297cdeb1c3bde0d52a2728aaf5b82ff9a2f0b633637bb0918eaace09.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "68d41d4d2600809632216b64f89c635c061d2f6f0c6d65db35e425065fcca1f2", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e28be81dc5a41846fe7482d713d29390496136d4e1e9a80038b9623d85e96f9d", "generation_seconds_batch": 15.685543218976818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6882017254829407, "target_z": 0.6445312283620296, "ce": 6.3641486167907715, "genuineness": 4.356721878051758, "identity": 0.7300641536712646, "hypothesis": "J'ai trouvé la 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_Teasing/68d41d4d2600809632216b64f89c635c061d2f6f0c6d65db35e425065fcca1f2.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "68faf430d370a19e61d18864e4963975240a774d6cc5b93485a6ce49e47f09f6", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7e738f42b4f67077a10a68e7f19eab2c1c6f8bb81785665aa166abddac5b155e", "generation_seconds_batch": 23.22472648101393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.820603609085083, "target_z": 0.8906249549930215, "ce": 6.086154937744141, "genuineness": 4.118232727050781, "identity": 0.5956395268440247, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/68faf430d370a19e61d18864e4963975240a774d6cc5b93485a6ce49e47f09f6.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "692849d7fbaf76e4deae59ab41e3d858484ec0bb3adb056bf9da4eaf827596f8", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e1ec304b9706252852b186b2669bc2d67bed13f343d2d1f0616823b3309e1232", "generation_seconds_batch": 19.26268037094269, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0517815351486206, "target_z": 1.3203124774965107, "ce": 6.324435234069824, "genuineness": 4.093128204345703, "identity": 0.3084845542907715, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/692849d7fbaf76e4deae59ab41e3d858484ec0bb3adb056bf9da4eaf827596f8.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "698ed5423057d7e397554549ac4f80f0b9689c4335a70bba590c2962d0329c52", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c806e6b9425652569036401dd75a6630d2f2edf22c13fcc97d12f62e57c82d29", "generation_seconds_batch": 23.92317056306638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4594953060150146, "target_z": 2.0781249688413226, "ce": 6.054384231567383, "genuineness": 4.099404335021973, "identity": 0.518968939781189, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/698ed5423057d7e397554549ac4f80f0b9689c4335a70bba590c2962d0329c52.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "6a07a785c9b5fdac2b2350fd5cc04c07dfa7879945deb03162054179c05dedc1", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8265a4eaa4f92d2ce84ea81c6d456d493b521c18d52244694e92065f58d01459", "generation_seconds_batch": 18.962152605992742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3502111434936523, "target_z": 1.8749998615169894, "ce": 6.054384231567383, "genuineness": 4.093128204345703, "identity": 0.40553778409957886, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/6a07a785c9b5fdac2b2350fd5cc04c07dfa7879945deb03162054179c05dedc1.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "bd51b8cd422b35c2da73202e279d96c81177742d434b67d15ef9853b2bd4e4e7", "generation_seconds_batch": 16.90953200205695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08293592929840088, "target_z": -0.4804687439413683, "ce": 6.395919322967529, "genuineness": 4.042920112609863, "identity": 0.33947131037712097, "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_Teasing/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "6a9e793b4548aa33166c2f467d1d2654fe1a740776f3cae458263db5df6c262c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2cf94a4a13021003e6f88b9f8ed44ba94fc29b867bc768907ffa0fb092e9379f", "generation_seconds_batch": 21.426194777945057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8079938888549805, "target_z": 0.8671874255653819, "ce": 6.078212261199951, "genuineness": 4.325342178344727, "identity": 0.6264095902442932, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/6a9e793b4548aa33166c2f467d1d2654fe1a740776f3cae458263db5df6c262c.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "6ab1e9e59e9f1c22de6f3acf3b603adbee67ef1f42e0d139a7d95f0fe6832cce", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d303546bff47d1e93f872d6470d8019927cee5cc8c6b73eb47355f696146124a", "generation_seconds_batch": 23.91805508104153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7032829523086548, "target_z": 2.5312500207724518, "ce": 6.070269584655762, "genuineness": 3.860914945602417, "identity": 0.3983197808265686, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/6ab1e9e59e9f1c22de6f3acf3b603adbee67ef1f42e0d139a7d95f0fe6832cce.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "115501c0dd5321d84ad72d5897f6e3edff6863d541d0492bd76c3bbf17a172e6", "generation_seconds_batch": 19.27918820094783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14388282597064972, "target_z": -0.3671875086551882, "ce": 6.2767791748046875, "genuineness": 4.582659721374512, "identity": 0.6349595785140991, "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_Teasing/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "6bc0319a75d4f9457c91b517da27b0c97bb26816cacc513dab310ce96d47af1f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8bf7328a5d75efe8998e7a5a6a0713c04f104e940b222af14a95159389cd0dd0", "generation_seconds_batch": 17.80272288096603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5015276670455933, "target_z": 2.1562499930758494, "ce": 6.165581703186035, "genuineness": 4.030367851257324, "identity": 0.37310874462127686, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/6bc0319a75d4f9457c91b517da27b0c97bb26816cacc513dab310ce96d47af1f.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "6bc23f65d56847147191ab6cec6759c863b3fb10cbfcaf79d1ff183e87adf93c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c2b7758dfd6bac7b3eff757d5c651c004e1036cbb7634983080da087e6ce074c", "generation_seconds_batch": 24.626590294996276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28784361481666565, "target_z": -0.09960938928106046, "ce": 6.0305562019348145, "genuineness": 4.243753433227539, "identity": 0.46501898765563965, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/6bc23f65d56847147191ab6cec6759c863b3fb10cbfcaf79d1ff183e87adf93c.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "6bcc212a51b59f206f9804ea462b4a4eeeb139581769e278a1915aeaa6dbfcd3", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "bbdc2218ea3ec8702074ae42143d6e59333aaefb257bcb848d93cc3866f4ba6a", "generation_seconds_batch": 26.07975068408996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7869777679443359, "target_z": 0.8281250242345268, "ce": 6.292664527893066, "genuineness": 4.174716949462891, "identity": 0.6480298042297363, "hypothesis": "J'ai trouvé la 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_Teasing/6bcc212a51b59f206f9804ea462b4a4eeeb139581769e278a1915aeaa6dbfcd3.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "6c5b80a096faaa4b5b6522aab3508b8262e07d9dfca1d408409a3ad4a67bc396", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "95619697de7e57611d25c996c8b124e2e278de3f7c7b02803cf6b12de479633c", "generation_seconds_batch": 25.851031793048605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6111817359924316, "target_z": 4.218750145407161, "ce": 6.006728172302246, "genuineness": 4.174716949462891, "identity": 0.6240825653076172, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/6c5b80a096faaa4b5b6522aab3508b8262e07d9dfca1d408409a3ad4a67bc396.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "6ca99874252730b6d3a589ec043e4f4e0688bf57e709f3e89b0dbe4c8e793874", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b9deadbd5667c2dab3b32c2b2b8cd67ddde88207f3d406777fd04e809c441c3d", "generation_seconds_batch": 24.23947368899826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1862850189208984, "target_z": 1.5703124221033065, "ce": 6.0146708488464355, "genuineness": 4.137060642242432, "identity": 0.5633119344711304, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/6ca99874252730b6d3a589ec043e4f4e0688bf57e709f3e89b0dbe4c8e793874.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "6d1d8ba1a12e58a9626901d1a946af578fed533be897647a155fd5e7f9df5149", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b01b63737a6af9af3f3654e999cd76e5ab5eb96d297157845323dab41d8529e1", "generation_seconds_batch": 24.301285030087456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5183405876159668, "target_z": 2.187499958455097, "ce": 6.268836498260498, "genuineness": 3.9550557136535645, "identity": 0.3442184329032898, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/6d1d8ba1a12e58a9626901d1a946af578fed533be897647a155fd5e7f9df5149.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": "6d57c68d7d0450abda04bc5d8b47572c46e6e268dfdf4c3ba5be1b1bac6ebc2c", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7353bd370037791263e3649467b4791dfb78182497b580e44722b91c8238ba3b", "generation_seconds_batch": 25.478480313904583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5943686962127686, "target_z": 4.1874999584550965, "ce": 6.205295085906982, "genuineness": 4.111956596374512, "identity": 0.7174913287162781, "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_Teasing/6d57c68d7d0450abda04bc5d8b47572c46e6e268dfdf4c3ba5be1b1bac6ebc2c.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "6dbcffd67fd59df518f3161d247084531eaf4187ced51e3216c0950aec05dcc6", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "64a8ba36310df136ab02b1639418c9de8a3502314aa444458a2659e2bc642f64", "generation_seconds_batch": 21.06776524905581, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.820973515510559, "target_z": 2.75, "ce": 6.1894097328186035, "genuineness": 4.061748504638672, "identity": 0.5735349655151367, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/6dbcffd67fd59df518f3161d247084531eaf4187ced51e3216c0950aec05dcc6.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": "6eb5174c500a236d1cc4e44b0bb482124b7c831f455aa4082ec7efa330ae8ab2", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c45a8e1f982ea2bfc954f6e55b63dcaab6fa8a34a88bfb8e0217e496b7c4160c", "generation_seconds_batch": 19.745656339917332, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3207886219024658, "target_z": 1.8203125882829192, "ce": 6.340320587158203, "genuineness": 3.923675537109375, "identity": 0.49519723653793335, "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_Teasing/6eb5174c500a236d1cc4e44b0bb482124b7c831f455aa4082ec7efa330ae8ab2.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": "6ee497dd1a51fa5a929c23e88ba28f3396ab46ece263ce23c0867734501fd9e3", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b636bd4cb02c9578c35963c58a37c298145cb31a5f207dc0767373ffa08fc5da", "generation_seconds_batch": 24.17679652001243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.417462944984436, "target_z": 1.9999999446067958, "ce": 6.23706579208374, "genuineness": 4.218649387359619, "identity": 0.5122504234313965, "hypothesis": "Celica a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/6ee497dd1a51fa5a929c23e88ba28f3396ab46ece263ce23c0867734501fd9e3.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "6f2f55698f3c635803bd074748788f88e56d91c9e9c0676b2f5ca8d0c8815e9d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "826de5dfa600274c520965f06e7311ebc3b8d5d81396c26dbebb0868fafb50ff", "generation_seconds_batch": 23.70765515801031, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5271170139312744, "target_z": 4.062500096938107, "ce": 6.41180419921875, "genuineness": 4.105680465698242, "identity": 0.6993328928947449, "hypothesis": "Ah Jovela Petite Boite. We've got ensemble what contiene.", "wer": 0.8947368421052632, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/6f2f55698f3c635803bd074748788f88e56d91c9e9c0676b2f5ca8d0c8815e9d.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "6f8156750e5ea722efabfa796bc1973601c8a08af08efb9efde3a2b0696e8c95", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "733c3d5c80bcd8d8b2e6fd23c2cf26170032de189e245393ba5d6d18e6e816fc", "generation_seconds_batch": 21.505957082961686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5943686962127686, "target_z": 4.1874999584550965, "ce": 6.070269584655762, "genuineness": 3.9927117824554443, "identity": 0.6391801834106445, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/6f8156750e5ea722efabfa796bc1973601c8a08af08efb9efde3a2b0696e8c95.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "6fc0a20c1c791271f197d943b6d750f3f6dad69022fa68414549753cfecc4eac", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7c5eb08ae3341d6018fc0046964de41ec3bd005b623d0490278e64cb65ec0af5", "generation_seconds_batch": 17.980288111022674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1274397373199463, "target_z": 1.4609374324895323, "ce": 6.332377910614014, "genuineness": 4.118232727050781, "identity": 0.3981897532939911, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/6fc0a20c1c791271f197d943b6d750f3f6dad69022fa68414549753cfecc4eac.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": "701bcda6d125724b2b8939f014a0b66846e09d3c82092da00780b1cf94e775a9", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e7a579f1332aca5b243d0aee90df63fcbed572144ba1c3f33c1b76a348e31b97", "generation_seconds_batch": 25.79937245300971, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2829594612121582, "target_z": 1.75, "ce": 6.046441555023193, "genuineness": 4.080576419830322, "identity": 0.6511839628219604, "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_Teasing/701bcda6d125724b2b8939f014a0b66846e09d3c82092da00780b1cf94e775a9.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": "70495c961314e496c0873459113b8cd4eb48cdcbea1fc56a01cade6d058292e2", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b453fe17097affb633c9e904d29675a5c37d988ccd91bc0d3aba2510ddfea2f", "generation_seconds_batch": 28.608841360080987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1568623781204224, "target_z": 1.5156249272964195, "ce": 6.284721851348877, "genuineness": 3.961331605911255, "identity": 0.48375535011291504, "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_Teasing/70495c961314e496c0873459113b8cd4eb48cdcbea1fc56a01cade6d058292e2.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "7084a74da73bb581683b77517b3c986a9f8a5c57f435e25da3243a2d293c31cb", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "85c0459211de290d7361c03acfec00c40549d3000ddc50bdfa038081b24b0caf", "generation_seconds_batch": 23.288150364998728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1824517250061035, "target_z": 3.4218750311586774, "ce": 6.1894097328186035, "genuineness": 4.118232727050781, "identity": 0.3315201997756958, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7084a74da73bb581683b77517b3c986a9f8a5c57f435e25da3243a2d293c31cb.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "71686dd557b38cefa2bfa290210f3bebdd9cd12dacc9a3efdfba68d32c3cef4e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6e0caf2dfcc90869932d030d32677f5bcd779e1ab5cff788b4893034e48e0c0b", "generation_seconds_batch": 17.880569062079303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5435600280761719, "target_z": 2.2343750173103762, "ce": 6.133810997009277, "genuineness": 4.18726921081543, "identity": 0.5010536909103394, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/71686dd557b38cefa2bfa290210f3bebdd9cd12dacc9a3efdfba68d32c3cef4e.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": "718a56ff55ab67c68a80a4a54d48e948e902bbb9ae481f42b35bfcc874f6b378", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "96f38b81ce938a25a259b4149dd82d1cc1dc0dc56b33953c3042ee21c5190f00", "generation_seconds_batch": 17.65179327002261, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8794488906860352, "target_z": 0.9999999446067958, "ce": 6.300607204437256, "genuineness": 4.381826400756836, "identity": 0.5500921607017517, "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_Teasing/718a56ff55ab67c68a80a4a54d48e948e902bbb9ae481f42b35bfcc874f6b378.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "721c63d5284c8c42d987ae3b10e20b8297fd5dd1b2c939742e5a060faab7102e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "534d99e517573a9a2d63ad674c3f69c9ffa04b6b90447a060652f7355df83afa", "generation_seconds_batch": 23.21062255895231, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.228317379951477, "target_z": 1.6484374463378335, "ce": 6.133810997009277, "genuineness": 3.9676074981689453, "identity": 0.6834412217140198, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/721c63d5284c8c42d987ae3b10e20b8297fd5dd1b2c939742e5a060faab7102e.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "7259a242fb7876d0ee8fb7691ac87b08c8858d18526b51b99a5a248f83f839c9", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "02ac9ce77e39fe9bd0651c0c5db42e3a8c6890cafb581394768bd0a0b5c5f59e", "generation_seconds_batch": 33.34550406807102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7911809682846069, "target_z": 0.8359374601861345, "ce": 5.919358730316162, "genuineness": 4.256305694580078, "identity": 0.5921273231506348, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7259a242fb7876d0ee8fb7691ac87b08c8858d18526b51b99a5a248f83f839c9.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "72a5d567f6e330dfd0874a79fbecb904d49f7ee9f50fbfc76d497bf37b440b2f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c20b8129b715856632a7d69cfb42156f9251ef626f51f25607fd68dd505edab4", "generation_seconds_batch": 23.247760772006586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.190488338470459, "target_z": 1.578125079627731, "ce": 6.324435234069824, "genuineness": 4.268857479095459, "identity": 0.6160345077514648, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/72a5d567f6e330dfd0874a79fbecb904d49f7ee9f50fbfc76d497bf37b440b2f.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "73fc0d894be13cb2f70e4a9812cd2432e0893d8a108fff94f61a8d8ebed84c65", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "79fe4afd921b901ef9db0871b24003be9b19239ed8c77955ee8fd50e81d03075", "generation_seconds_batch": 23.936593572958373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.19469153881073, "target_z": 1.5859375155793387, "ce": 6.268836498260498, "genuineness": 3.6789097785949707, "identity": 0.22715291380882263, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/73fc0d894be13cb2f70e4a9812cd2432e0893d8a108fff94f61a8d8ebed84c65.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": "73ff91643d8c14aae28821711a3d51cce9a4f4430a09769f5b1624c322c039ef", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6acbaf150dc7b2cd5a0064ed868ded09a49672647e3446cbde53e0f7f7c2b705", "generation_seconds_batch": 18.423910591052845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.636031150817871, "target_z": 2.406249937682645, "ce": 6.324435234069824, "genuineness": 4.086852550506592, "identity": 0.27335458993911743, "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_Teasing/73ff91643d8c14aae28821711a3d51cce9a4f4430a09769f5b1624c322c039ef.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "7433d27ee71a3ae809b19e95a0a6f61e27bfeea3798e27156f7bb14107e4b7c4", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7edb835159d493dd4c49860ff97fcae9297904ded8c258fae40f355051149526", "generation_seconds_batch": 22.57401869900059, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19011841714382172, "target_z": -0.28124999307584947, "ce": 6.348263263702393, "genuineness": 3.9801597595214844, "identity": 0.3023320138454437, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7433d27ee71a3ae809b19e95a0a6f61e27bfeea3798e27156f7bb14107e4b7c4.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": "754dcf0e964acb823a76618b19d220700708239a2f37fa42fa2d095d81aeae8e", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e8ab4b969031c76a642daff7d32ac43db1f99ffa673a28d1813470ee56503d1d", "generation_seconds_batch": 25.79937245300971, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1404194831848145, "target_z": 3.3437502284969676, "ce": 6.141753673553467, "genuineness": 3.9927117824554443, "identity": 0.6108429431915283, "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_Teasing/754dcf0e964acb823a76618b19d220700708239a2f37fa42fa2d095d81aeae8e.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "755af4390ee33f366eb1827a50afb948df7b47fa1ba98cfef3774ae0606a639e", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "783764e4759be5fd30cee4ac67cb2faab2fd50f59fbe082bb93cc90afbc03627", "generation_seconds_batch": 19.14694251003675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6440677642822266, "target_z": 0.5624999861516989, "ce": 6.022613525390625, "genuineness": 4.13078498840332, "identity": 0.6778616309165955, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/755af4390ee33f366eb1827a50afb948df7b47fa1ba98cfef3774ae0606a639e.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "75dd6977477f7fa82be02bdacae86db6921a27cb86f7d68aa26425ec0a188070", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "57472dc73cb5b0a2aaf33412c80d66780f5e666a82739308e2416a90e1aaf5ae", "generation_seconds_batch": 23.31615127902478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6444376707077026, "target_z": 2.4218750311586774, "ce": 6.022613525390625, "genuineness": 4.055472373962402, "identity": 0.4353065490722656, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/75dd6977477f7fa82be02bdacae86db6921a27cb86f7d68aa26425ec0a188070.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "75e6f97e0a9b2d83fc8a0ab0e0076bcd459638e3ddec867531876e37c942c875", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "917ff38398206504a8c359a11cfddc5e36f88a644d428bfbb9d342bffc34cf22", "generation_seconds_batch": 26.72880255698692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4763082265853882, "target_z": 2.10937493422057, "ce": 6.133810997009277, "genuineness": 4.105680465698242, "identity": 0.6337849497795105, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/75e6f97e0a9b2d83fc8a0ab0e0076bcd459638e3ddec867531876e37c942c875.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": "7683f6ed35053a9ff80641c8eb7a3da9535e790eec6abf25ab89684859572c22", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "29c40723037c092c32a3d1397ee8260c21797bd14d7772046ead52fff0b8cd1d", "generation_seconds_batch": 25.512392443954013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6780635118484497, "target_z": 2.484374961917172, "ce": 6.459460258483887, "genuineness": 4.080576419830322, "identity": 0.2780124843120575, "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_Teasing/7683f6ed35053a9ff80641c8eb7a3da9535e790eec6abf25ab89684859572c22.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "76b6c7620dcb7770051dba857d3215137999e4017977046e252224d4e31cb126", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "216beb22f41a48031c5efdbdde0d9f61ed7feffdda0af0bfa076cd46847da999", "generation_seconds_batch": 15.685543218976818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7974858283996582, "target_z": 0.8476562248999543, "ce": 6.268836498260498, "genuineness": 4.557555198669434, "identity": 0.8360688090324402, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/76b6c7620dcb7770051dba857d3215137999e4017977046e252224d4e31cb126.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "7709ba21b99f216443820a04e3710d32b50e15b9e85f9715d7d004658a1177ee", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1f49b7aa22689844170104f74cf22f332f7aa2bd2efec909ffe2db601a4c9832", "generation_seconds_batch": 25.74262660194654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.577185869216919, "target_z": 2.296874948068871, "ce": 5.871703147888184, "genuineness": 3.9676074981689453, "identity": 0.43820706009864807, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7709ba21b99f216443820a04e3710d32b50e15b9e85f9715d7d004658a1177ee.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "771548024d7162335a4014d2845da5c26b6428423c97de3a9848583665e39aa5", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b499ed6fe0daab56cd39026797d40c05dac9e32dce043f5f04c3e34dd079d5a2", "generation_seconds_batch": 26.016615148982964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6440677642822266, "target_z": 0.5624999861516989, "ce": 6.372091293334961, "genuineness": 4.042920112609863, "identity": 0.4250909686088562, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/771548024d7162335a4014d2845da5c26b6428423c97de3a9848583665e39aa5.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": "7727b5c8b5d35108abf1e0bd48c21f930b66f279034b834e988fe877115461ba", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8f3f4432b29ba897884920b00283b2c1cdbd054fd0ce4cda5b38f8123896d205", "generation_seconds_batch": 23.38063573196996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8689408302307129, "target_z": 0.9804687439413683, "ce": 6.483288764953613, "genuineness": 3.860914945602417, "identity": 0.3967582881450653, "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_Teasing/7727b5c8b5d35108abf1e0bd48c21f930b66f279034b834e988fe877115461ba.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "0eafd27ec5cd726fd17a527c9d7cc80125ea025de8e291a000c76e4f2d57b600", "generation_seconds_batch": 19.806637458968908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06612297892570496, "target_z": -0.5117187647138198, "ce": 6.109982967376709, "genuineness": 4.68307638168335, "identity": 0.8038179874420166, "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_Teasing/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "77b0a4dfc475b84f68d8a7e5a026812ad80cd8bf4fd86387909030c2e0756365", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ae7ad3a2b2e6b6e3651a7d2da7c74190d50b37dab209abab1871f2f9d7992330", "generation_seconds_batch": 19.219456227030605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7848761081695557, "target_z": 0.8242186954723146, "ce": 6.332377910614014, "genuineness": 3.9173994064331055, "identity": 0.5838412046432495, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/77b0a4dfc475b84f68d8a7e5a026812ad80cd8bf4fd86387909030c2e0756365.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "784607e5eba6490c8b4ee0d25c42ceb4b233c9dbf515b61670963f17bb7c32ad", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0fd89cddd5bc32b554e63e0a440d423c434db8ae63f9a6667791343aae691a57", "generation_seconds_batch": 24.962993282009847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8798187971115112, "target_z": 2.8593749896137743, "ce": 6.038498878479004, "genuineness": 4.268857479095459, "identity": 0.6737622022628784, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/784607e5eba6490c8b4ee0d25c42ceb4b233c9dbf515b61670963f17bb7c32ad.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "784b243a0cbfa7937c648ee48d3628dd360e9434ae1f1571c838fff0f1c158e0", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f777c6bc378b1e3d6e50f6e45fe6e082b74c55242afec00fd79d8acc47153782", "generation_seconds_batch": 17.928974578971975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.413259744644165, "target_z": 1.9921875086551881, "ce": 6.1894097328186035, "genuineness": 4.394378662109375, "identity": 0.6776753067970276, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/784b243a0cbfa7937c648ee48d3628dd360e9434ae1f1571c838fff0f1c158e0.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "78914d2d2dab3479a393bff19696ca32f200e2255884cc807351c50039d4eab5", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "945a7be2bf1fe66f6235eca98668dd2f90115b40a859eaea4c2b8429d3c80dce", "generation_seconds_batch": 17.528949655010365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3866196274757385, "target_z": 0.08398435119823255, "ce": 6.292664527893066, "genuineness": 4.419482707977295, "identity": 0.7112038135528564, "hypothesis": "J'ai trouvé la 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_Teasing/78914d2d2dab3479a393bff19696ca32f200e2255884cc807351c50039d4eab5.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "7928b6ef4e359bf3d99843e311fc8060fd6689e9617638aa1ff66111d440982d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "42ad45b7a98167a1830f85d42cb45f344a3f52c1fc15bec20fba761377e61ea6", "generation_seconds_batch": 24.20458872197196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0770009756088257, "target_z": 1.3671875363517902, "ce": 6.435632705688477, "genuineness": 4.13078498840332, "identity": 0.3451388478279114, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7928b6ef4e359bf3d99843e311fc8060fd6689e9617638aa1ff66111d440982d.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "79392f18ff810844286864b72d16fd51dd4c9e18a7fdf13e116a9eaf21069074", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "046e6f1d55a3beac6dc008d7f6e52489211e61f93eda43bfc60dc8bb66c9c672", "generation_seconds_batch": 24.4132035470102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2076711654663086, "target_z": 3.4687500900139567, "ce": 6.022613525390625, "genuineness": 4.017816066741943, "identity": 0.6622047424316406, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/79392f18ff810844286864b72d16fd51dd4c9e18a7fdf13e116a9eaf21069074.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "c5925755e8dc742aafd99f3fd83b59918989231a468987af7ead6e698779141d", "generation_seconds_batch": 19.941399262053892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030395478010177612, "target_z": -0.5781250242345268, "ce": 6.1894097328186035, "genuineness": 4.306513786315918, "identity": 0.695348858833313, "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_Teasing/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "7957ba82d79905dd08198766bab7164ec76126085ea21974bdb01d18c20715af", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0bd80c9751f0c727886daf3f6673b6c1c4718c2adb940fa41c9f5f5de9fd3407", "generation_seconds_batch": 17.67884777497966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2619433403015137, "target_z": 1.710937598669145, "ce": 6.348263263702393, "genuineness": 3.961331605911255, "identity": 0.8619462251663208, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7957ba82d79905dd08198766bab7164ec76126085ea21974bdb01d18c20715af.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": "79f462d028b634632e6c59ba8942748625ab6bb8fce06282d1393be183112c5a", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "34f6bf84c30ca166c5d42aab467dffb391c4431b4cce64d5dcbbcedd66cbac31", "generation_seconds_batch": 17.44144995592069, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3628208637237549, "target_z": 1.8984373909446293, "ce": 6.133810997009277, "genuineness": 4.243753433227539, "identity": 0.7037070989608765, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici près de la grand bibliothèque. Nous la remettrons afin le déjeuner.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/79f462d028b634632e6c59ba8942748625ab6bb8fce06282d1393be183112c5a.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "7a4199c7bbf718d9401a3f177e8ece0759c56e616f4b964c3f1cbab6153c12d3", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "70915d04a68384eae14d0ea34007b6cda4d23df4f277949b647e4c462a96d8bd", "generation_seconds_batch": 26.07975068408996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5855923891067505, "target_z": 2.312500041544903, "ce": 6.173524379730225, "genuineness": 4.306513786315918, "identity": 0.6025710701942444, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7a4199c7bbf718d9401a3f177e8ece0759c56e616f4b964c3f1cbab6153c12d3.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "7a82dcb8d2bfeb7b0db44c7f296aa91aeabb7b04b8ce83bd8b74394d03337ccb", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4edadd84b42ffc4816ef77c4cec40b5c9804fa772c1c0db37e3b51abd08358ad", "generation_seconds_batch": 17.413270491058938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.610811710357666, "target_z": 2.359374878827366, "ce": 6.38797664642334, "genuineness": 4.444586753845215, "identity": 0.2993658483028412, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7a82dcb8d2bfeb7b0db44c7f296aa91aeabb7b04b8ce83bd8b74394d03337ccb.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "7ad0cd50b0a8e5102054201343a34941bb1c5793a5824a8fac0dead16bd56bd0", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "da41768cd3b356d05f2cc3498900469cc0dfa721231154df25f16328e6c9f350", "generation_seconds_batch": 25.604592517018318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5600030422210693, "target_z": 0.4062499376826452, "ce": 6.260893821716309, "genuineness": 4.406930446624756, "identity": 0.700131893157959, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7ad0cd50b0a8e5102054201343a34941bb1c5793a5824a8fac0dead16bd56bd0.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "7afe42d22ec3900ac8acabcf79d3898a6215c32f5a286f6dced617ac5d89a61c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "428d0f407f4b89d0aa1c0b8df14359af992fe0152043bafb086e6aab1690cc8e", "generation_seconds_batch": 24.3086674970109, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2955691814422607, "target_z": 1.7734375294276397, "ce": 6.205295085906982, "genuineness": 3.860914945602417, "identity": 0.26931822299957275, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7afe42d22ec3900ac8acabcf79d3898a6215c32f5a286f6dced617ac5d89a61c.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "7b1e07c469b6495621966a62683bfc85311dd198473bce37d57cb145aa172e57", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2f238ebd11ca03d4f661f11ba1b156b766f12a4d8afaf0b5e4f41b5ecc0a948d", "generation_seconds_batch": 23.93591421400197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0815742015838623, "target_z": 3.2343752388831932, "ce": 5.847874641418457, "genuineness": 3.9676074981689453, "identity": 0.48405537009239197, "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_Teasing/7b1e07c469b6495621966a62683bfc85311dd198473bce37d57cb145aa172e57.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "7b3230382e0cd26735637b510861382402bb73214bed8243ca0d39444a75ff34", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f29dc53253befc6d9501453e18a0f1cc118f53dddb0c41ec0e5f72558062914c", "generation_seconds_batch": 24.435898488969542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4679017066955566, "target_z": 2.093749840744538, "ce": 6.173524379730225, "genuineness": 4.3504462242126465, "identity": 0.7925416231155396, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7b3230382e0cd26735637b510861382402bb73214bed8243ca0d39444a75ff34.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "7ba3c9036fdb91b5eedb9d26d25070f6f2a36b9c854157af8663a0fec97c2b9f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "255ed6c9ab55204929ede8ee101f2e93d58d1f4eabe36bc762ce3cadbf3f1e00", "generation_seconds_batch": 23.00366273301188, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.989102840423584, "target_z": 3.0624998753652903, "ce": 6.117925643920898, "genuineness": 4.068024158477783, "identity": 0.6212016940116882, "hypothesis": "Ik 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_Teasing/7ba3c9036fdb91b5eedb9d26d25070f6f2a36b9c854157af8663a0fec97c2b9f.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "7bca7e0a92fe11f3c03943d940cb17c482ca81b8341c43b23d8e36d07cb3aeb4", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b356af894a0320cb3b098cb87e18619b7e8716a91ca9f3cce9294d30d1cbd42c", "generation_seconds_batch": 17.212999845971353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9302575588226318, "target_z": 2.9531248857515164, "ce": 6.133810997009277, "genuineness": 4.068024158477783, "identity": 0.6727146506309509, "hypothesis": "Ik 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_Teasing/7bca7e0a92fe11f3c03943d940cb17c482ca81b8341c43b23d8e36d07cb3aeb4.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "7c51f1f091c7115c866afc45f558d684551ed1801d08a3e465f1a3e308c72ad0", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f32641fc282e1f9d2d41540540630fe27d15548b87d05d6a97761f6930b0ed37", "generation_seconds_batch": 23.79222538403701, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5855923891067505, "target_z": 2.312500041544903, "ce": 6.173524379730225, "genuineness": 4.331617832183838, "identity": 0.6188756823539734, "hypothesis": "J'ai trouvé la 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_Teasing/7c51f1f091c7115c866afc45f558d684551ed1801d08a3e465f1a3e308c72ad0.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "7cf0c70ad73461e45669aff7c2dcb6fccc8c582cb366cb594550f66f557aff0d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7928655fba48eb8d314c6fc20596a312077c11f705662f637fdbb58d3b1cb2d8", "generation_seconds_batch": 21.921728587010875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.602405309677124, "target_z": 2.3437500069241506, "ce": 6.340320587158203, "genuineness": 4.381826400756836, "identity": 0.685353696346283, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7cf0c70ad73461e45669aff7c2dcb6fccc8c582cb366cb594550f66f557aff0d.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "7d4bb8638e77ca46ca207b16999693c7ec6ec595d52fdafd4236337e107a595e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6a7c9962dacabc24b98e8a7550e0666fd6952ab25f7b9c382655854000bbd453", "generation_seconds_batch": 22.69566733308602, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.384207010269165, "target_z": 3.7968750588552793, "ce": 6.197352409362793, "genuineness": 3.5596652030944824, "identity": 0.26579490303993225, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7d4bb8638e77ca46ca207b16999693c7ec6ec595d52fdafd4236337e107a595e.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "7e50e68ea31cc2f8586113f0f812b8dd521aea698e1f669e8e5fcbace9153df3", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1d8ff5c2891b3f72af5279f2d7dfb41fd1af95dd7aaf157c7aae0527187576d7", "generation_seconds_batch": 25.58080070198048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8798187971115112, "target_z": 2.8593749896137743, "ce": 6.149696350097656, "genuineness": 3.8169827461242676, "identity": 0.33153873682022095, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7e50e68ea31cc2f8586113f0f812b8dd521aea698e1f669e8e5fcbace9153df3.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "7e6f95bc874c33d51fc81e6f5dd2da7e442d1d7dd8783b9fcd970b7f313215bb", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a4ce4361036f2250c3c77144859490bcc18012b778893ab4d49c224fb67ab5a2", "generation_seconds_batch": 24.626590294996276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7890793681144714, "target_z": 0.8320312422103306, "ce": 6.149696350097656, "genuineness": 4.168440818786621, "identity": 0.6794482469558716, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7e6f95bc874c33d51fc81e6f5dd2da7e442d1d7dd8783b9fcd970b7f313215bb.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "7e75fceedf73153afb30d4fa56a0827bceccac683d57ce8b07cd3161f908c51f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6ba1a23b7f84d929131075c3fcf0fffc9c450541b89f93762276dd5dbea7d071", "generation_seconds_batch": 23.112677811062895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8079938888549805, "target_z": 0.8671874255653819, "ce": 6.229123115539551, "genuineness": 3.7793264389038086, "identity": 0.3840121030807495, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7e75fceedf73153afb30d4fa56a0827bceccac683d57ce8b07cd3161f908c51f.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": "7ecca4ed9f4b94717fe777aff608d659f3d22ad661a88e772b4c753e0651f114", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ef9302a16b4774a62d369c7af39502bc9cd3f531f989b65e8c0bf8204e8531b3", "generation_seconds_batch": 24.039263216080144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5925781726837158, "target_z": 0.46679692563285075, "ce": 5.998785495758057, "genuineness": 4.344170093536377, "identity": 0.41092151403427124, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam neem ze mee als je weggaat.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7ecca4ed9f4b94717fe777aff608d659f3d22ad661a88e772b4c753e0651f114.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "7f02e92611cc520a6d6f5b982dc8b47412af101107728387dac9da14cba50fc0", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "8bd9a471f3ffa5b696cfa94242b810b5a4889920418dc3e75774045f3534bf96", "generation_seconds_batch": 23.114872189005837, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.40942645072937, "target_z": 3.843750117710559, "ce": 5.990842819213867, "genuineness": 3.9299514293670654, "identity": 0.572966456413269, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7f02e92611cc520a6d6f5b982dc8b47412af101107728387dac9da14cba50fc0.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "7f0f9eeed3de70096e9d4b9974b641847d1d794a05412758d4c47b23e070ff0a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d6d9d25f5234e746c894220966290e65c74a265feffefb19b0ab8d073b032ea8", "generation_seconds_batch": 22.73186831199564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5852224826812744, "target_z": 0.45312499653792476, "ce": 6.252951145172119, "genuineness": 4.425758361816406, "identity": 0.5545583367347717, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7f0f9eeed3de70096e9d4b9974b641847d1d794a05412758d4c47b23e070ff0a.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "7f37055e681a97e898f13ffa7f9d87fe05acf30f33e649dfba1ebcd3a500d410", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "812c2a11671fffd6312a8853d6b1d835112bd96421a7aa81de7303ed16d3057c", "generation_seconds_batch": 22.502354993019253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8125669956207275, "target_z": 2.7343749065239678, "ce": 6.086154937744141, "genuineness": 3.591045379638672, "identity": 0.222431480884552, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7f37055e681a97e898f13ffa7f9d87fe05acf30f33e649dfba1ebcd3a500d410.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "60171a071d8fe634f9d5123cd69e730183370f46bf892446ea36804163489a92", "generation_seconds_batch": 17.580216636997648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1134093850851059, "target_z": -0.42382811244997715, "ce": 6.427689552307129, "genuineness": 4.381826400756836, "identity": 0.4042789041996002, "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_Teasing/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.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": "7f76d086727954ad004bd4f2e04880151cd11d663c13db41be8881509f4f1cec", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ca62a149c586c358177d110fd0a430a5b78044f810be64867c49511acec04690", "generation_seconds_batch": 14.571391965961084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6948764324188232, "target_z": 2.5156249272964195, "ce": 6.165581703186035, "genuineness": 4.319066047668457, "identity": 0.6096448302268982, "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_Teasing/7f76d086727954ad004bd4f2e04880151cd11d663c13db41be8881509f4f1cec.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "7f934b64ec3b5f2c3acb3d4337fc2b387fa713567153d5ddb9da0799bf96279b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ce2707bcc275e1e80519632646acb74bc4f619ccba47f864bac88939beb736ff", "generation_seconds_batch": 24.022367710014805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5099340677261353, "target_z": 2.1718748649790647, "ce": 6.070269584655762, "genuineness": 4.2249250411987305, "identity": 0.550618052482605, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7f934b64ec3b5f2c3acb3d4337fc2b387fa713567153d5ddb9da0799bf96279b.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "7f991b1efe5be39c89018df889d489836ea3e1949e9422cd02a814e50041653e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "fb8b0fe9f75a0c4aa645a893871b97a5a353beaffbd3e53e7210b08a86c77afd", "generation_seconds_batch": 17.686070543015376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8377864360809326, "target_z": 2.7812499653792475, "ce": 6.078212261199951, "genuineness": 3.4937667846679688, "identity": 0.252294659614563, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/7f991b1efe5be39c89018df889d489836ea3e1949e9422cd02a814e50041653e.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "8053f5815a491c099359053a3d88820cbb7e945da74e06b188a0f4ad4b4d8e61", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fd4c3cb4d09c0120e45445cea1ff20cb8fdd2ba975a56e76b881bb74c54a6f7f", "generation_seconds_batch": 25.87462053494528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7116893529891968, "target_z": 2.546874892675667, "ce": 6.292664527893066, "genuineness": 3.9173994064331055, "identity": 0.1926315277814865, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8053f5815a491c099359053a3d88820cbb7e945da74e06b188a0f4ad4b4d8e61.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "738969923e49ccecaf54ac479f4a577a4803e7fcd69de20efab08d970d836778", "generation_seconds_batch": 18.777087180060335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10815533995628357, "target_z": -0.433593740479293, "ce": 6.284721851348877, "genuineness": 4.1998209953308105, "identity": 0.6381804943084717, "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_Teasing/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "81474924e3bf1b12f02c3df43d89f4cf0a30b58950c06f346efa90ca53d9654e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3cc6766b14535535e342006e44844a29f6a60ab4243cf423a5f0dba79531499e", "generation_seconds_batch": 15.369614523020573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4258694648742676, "target_z": 2.015625038082828, "ce": 6.157639026641846, "genuineness": 4.356721878051758, "identity": 0.5726994276046753, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/81474924e3bf1b12f02c3df43d89f4cf0a30b58950c06f346efa90ca53d9654e.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "8180333f2abacdaa9655c76854c6bc412ce91eed3e07ed108d422c53a4d47f13", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "786d59c2f487ce372e1060e8860db5b3cc1e2a6e194bd3d053bc13606c3756fb", "generation_seconds_batch": 16.687709343037568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4675319194793701, "target_z": 0.23437501731037633, "ce": 6.260893821716309, "genuineness": 4.218649387359619, "identity": 0.612919270992279, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8180333f2abacdaa9655c76854c6bc412ce91eed3e07ed108d422c53a4d47f13.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "81a173d8a1033e46aa801aa20402721b98f5a4d14dd39602f551e21bda3b04ae", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b823b8d835bf7ffc4fbf73f1832fbbf1627ba9af7f460b8394565ffa5c25a98b", "generation_seconds_batch": 23.40803610603325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7200958728790283, "target_z": 2.562499986151699, "ce": 6.268836498260498, "genuineness": 4.13078498840332, "identity": 0.3872271180152893, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/81a173d8a1033e46aa801aa20402721b98f5a4d14dd39602f551e21bda3b04ae.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "8251b575839e1ad878a10678c1cd0ab8e2f5da621b9b344095315f18f9130bc1", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ee01a01f5b446b4afce81de11687a842d4d5f0d7b16e05e76435c8196041d79c", "generation_seconds_batch": 23.36133496905677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7116893529891968, "target_z": 2.546874892675667, "ce": 6.0146708488464355, "genuineness": 3.873466968536377, "identity": 0.30873599648475647, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8251b575839e1ad878a10678c1cd0ab8e2f5da621b9b344095315f18f9130bc1.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "825d97af7b7341cd6801479b3a167c8ab6698d8b8fb69dc8086a32feb7526cd0", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "81f19ee3baebbeab5617ada8e494552f97509bc98094dbe61602ce6029ee110e", "generation_seconds_batch": 23.79760507598985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3887212574481964, "target_z": 0.08789062456724059, "ce": 6.205295085906982, "genuineness": 4.268857479095459, "identity": 0.27855464816093445, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/825d97af7b7341cd6801479b3a167c8ab6698d8b8fb69dc8086a32feb7526cd0.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "826a0bd952954b32308a69505952a74c1881ca591957677dbe09c1fcf26b66e5", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "40918b0efd2c3f0ae373649c11579a1c702087e0f6a881f4ef6a5d034d8027f0", "generation_seconds_batch": 25.730458584963344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6192182302474976, "target_z": 2.374999972303398, "ce": 6.252951145172119, "genuineness": 3.9550557136535645, "identity": 0.39619743824005127, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/826a0bd952954b32308a69505952a74c1881ca591957677dbe09c1fcf26b66e5.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "829b4e326b2f4236505ea5367d061bb2fc2d6f61f2386ae8e633da402bb72e70", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ed957af4451a5dcfb248a2f6448f03752eb013734f5fb7d8c9eee0c0e8ca5be1", "generation_seconds_batch": 22.897311302949674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.989102840423584, "target_z": 3.0624998753652903, "ce": 6.046441555023193, "genuineness": 3.9676074981689453, "identity": 0.12758904695510864, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/829b4e326b2f4236505ea5367d061bb2fc2d6f61f2386ae8e633da402bb72e70.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "82cbb493e4d2e41fc04f2cebdd4c79de30c66957ffc97afb8b06be1ba3576c7a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "59d641326a7b64f77b97b028c8ded179e0240c2d4b9a87aeb2a382fec22ee2b8", "generation_seconds_batch": 22.354152506915852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4682717323303223, "target_z": 3.953125107324333, "ce": 6.054384231567383, "genuineness": 4.143336772918701, "identity": 0.5048079490661621, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/82cbb493e4d2e41fc04f2cebdd4c79de30c66957ffc97afb8b06be1ba3576c7a.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "82d7c5bbb833c8a205473c8eafc8a8b529133725ed4d4fd5914e6c91b5ae18cf", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8b67253cd9e0b9c4b2d74681b1ca62c9f8bc099a627ff9d8f261e1fa8125af7a", "generation_seconds_batch": 17.322935087024234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1824517250061035, "target_z": 3.4218750311586774, "ce": 6.038498878479004, "genuineness": 3.71028995513916, "identity": 0.18588854372501373, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/82d7c5bbb833c8a205473c8eafc8a8b529133725ed4d4fd5914e6c91b5ae18cf.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": "8319e00d6a42c757eb737dd59134c6e529a994edff8b951b9dbcd192b946191b", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cdee9fc0c94ad01fa0e5576e5a600cf63f1bde161c1ec516c4e1f4fa7df854b8", "generation_seconds_batch": 17.340825080987997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9761233329772949, "target_z": 1.1796875225034893, "ce": 6.109982967376709, "genuineness": 4.231201171875, "identity": 0.6456928849220276, "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_Teasing/8319e00d6a42c757eb737dd59134c6e529a994edff8b951b9dbcd192b946191b.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "8341df28127b412abce4389b4417bc2e9fb2ebb8d0c7b89ff3f7f8762d39be30", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ca5760050d3bb2159ab70da94c89babb10dacdb4954dc6e420ed6430d593d69b", "generation_seconds_batch": 26.621667413972318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8545993566513062, "target_z": 2.8124999307584946, "ce": 6.316492557525635, "genuineness": 4.362998008728027, "identity": 0.3458664119243622, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8341df28127b412abce4389b4417bc2e9fb2ebb8d0c7b89ff3f7f8762d39be30.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "83fd92ace3f47ea1dc67a0e4d707cbe98cdb9f82f8db79ce57366857048433f0", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5e830e791713adbaa570e2cc7f7c2411431bf98b65e9284939fcc00ece2caa22", "generation_seconds_batch": 17.686070543015376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2665164470672607, "target_z": 3.578125079627731, "ce": 6.1894097328186035, "genuineness": 3.515732765197754, "identity": 0.45798730850219727, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/83fd92ace3f47ea1dc67a0e4d707cbe98cdb9f82f8db79ce57366857048433f0.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "849b8cd3d0e4650278b90340acce05e63ad93b0fdab760298d1605b41df112dc", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4e53234e025e91449609de66329edc533083b970270fb8ddb5c10ec79f9d7228", "generation_seconds_batch": 18.3912093230756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.636031150817871, "target_z": 2.406249937682645, "ce": 6.09409761428833, "genuineness": 3.9676074981689453, "identity": 0.5437182188034058, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/849b8cd3d0e4650278b90340acce05e63ad93b0fdab760298d1605b41df112dc.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "8506b8d401888dfb1c105d6f036a1d909a7eeb9a3abfaa67e4ca37a70c36ec09", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8d36f519460f419b0eef2f7e1b0d1ed6a6148fbc71ffa5b40f7186dc2efa78a0", "generation_seconds_batch": 25.899446246097796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.030765414237976, "target_z": 1.2812500761656558, "ce": 6.24500846862793, "genuineness": 4.3881025314331055, "identity": 0.6598873138427734, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8506b8d401888dfb1c105d6f036a1d909a7eeb9a3abfaa67e4ca37a70c36ec09.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "853876343678bf22f441f949c1e0b53329b83b7e17e729313d7826ef0ea8eabe", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3b3c075968c3f588f6431f359f5cda80a6da04b5ba19a088c8a9c3c7410ba2f5", "generation_seconds_batch": 23.112677811062895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2619433403015137, "target_z": 1.710937598669145, "ce": 6.038498878479004, "genuineness": 3.9048471450805664, "identity": 0.6192426681518555, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/853876343678bf22f441f949c1e0b53329b83b7e17e729313d7826ef0ea8eabe.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "85839102dff2e8bb1f7146bf145401af6eae30e48ba2f4b44e217e123f5ce419", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "34ba754373229b8e9fd99b91d3c724c85f14bb2e3aec3e9370a699bb45cfb6ad", "generation_seconds_batch": 28.803856368991546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.738640546798706, "target_z": 0.7382812352861802, "ce": 6.173524379730225, "genuineness": 4.545003414154053, "identity": 0.7168818712234497, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/85839102dff2e8bb1f7146bf145401af6eae30e48ba2f4b44e217e123f5ce419.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "85f0f0380deb2865322b56795970f5d372376d9adf7b559d69bd7642fbd557af", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c6be80921add57fe65d0bf7c18d80abf656ce50624f4e0a87fca3772a4f4694f", "generation_seconds_batch": 16.80379750893917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5267471075057983, "target_z": 2.203125051931129, "ce": 6.0305562019348145, "genuineness": 3.6349775791168213, "identity": 0.6695607900619507, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/85f0f0380deb2865322b56795970f5d372376d9adf7b559d69bd7642fbd557af.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": "85f3d9c6c556fca4bba1e648a9709311474e6088a2cba70c84e210a8d3484db0", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "77d44fa664d5dfbe158aaeaf46b4eac1e122d4c5311d6135b6c739c5920b3c2c", "generation_seconds_batch": 17.340825080987997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1316430568695068, "target_z": 1.468750090013957, "ce": 6.157639026641846, "genuineness": 4.325342178344727, "identity": 0.6703730225563049, "hypothesis": "J'écris le numéro sur l'enveloppe. Lis-bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.13636363636363635, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/85f3d9c6c556fca4bba1e648a9709311474e6088a2cba70c84e210a8d3484db0.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "860155491fa82ad31ddef8f0ce4b2eb40ef9a77782dd3442bb1e54da2c0e89f9", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8710a6b1e8f444b9e8e5a18f47f8d574af7e1f9632f03c5a542499eb85d5cff3", "generation_seconds_batch": 23.367534690070897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7537217140197754, "target_z": 2.624999916910194, "ce": 6.062326908111572, "genuineness": 4.168440818786621, "identity": 0.4140077233314514, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/860155491fa82ad31ddef8f0ce4b2eb40ef9a77782dd3442bb1e54da2c0e89f9.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "860bd5d5bae0c24057a7f606369d8a597c5e19ac23cc340dfaa3e6b25008e87e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "05d18f43dff2b01dbdab13508d9b1a21b4a35bf7e856c59e496b25de63bab185", "generation_seconds_batch": 15.92507423600182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3165853023529053, "target_z": 1.8124999307584948, "ce": 6.41180419921875, "genuineness": 3.860914945602417, "identity": 0.33956819772720337, "hypothesis": "I have found the little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/860bd5d5bae0c24057a7f606369d8a597c5e19ac23cc340dfaa3e6b25008e87e.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "86233b2c1ac5ad9d558fbbe0107ae3dd3354e9e94a54530812a7aee460bb69a0", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ebb04db1f4a60618e199621e0cf144d2787e6176c63b3f2f6a9477b059eeab78", "generation_seconds_batch": 22.384759754058905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1067934036254883, "target_z": 3.281249854592839, "ce": 6.109982967376709, "genuineness": 4.055472373962402, "identity": -0.02480139210820198, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/86233b2c1ac5ad9d558fbbe0107ae3dd3354e9e94a54530812a7aee460bb69a0.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "865945291f1d56b33a3eb2b4565ca81cfd7745cf6037d1c4cdb09a6e2cc6d04e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "55a40d06b6c85cb2a54b7c927dc3d828934a07685ab45993126e90d7355938d4", "generation_seconds_batch": 23.737654247903265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.434645891189575, "target_z": 3.8906251765658384, "ce": 6.086154937744141, "genuineness": 4.1998209953308105, "identity": 0.4609759449958801, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/865945291f1d56b33a3eb2b4565ca81cfd7745cf6037d1c4cdb09a6e2cc6d04e.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "86e765aec09a0125b2f5f10f3784d1880d63e70a4fc95b2c00ee974782dda738", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c34c70d5a6e880678f7360025e8feec2a2065095fb7d0f4f44a7ec97637c936e", "generation_seconds_batch": 23.201141300960444, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12917150557041168, "target_z": -0.3945312560586317, "ce": 6.062326908111572, "genuineness": 4.65797233581543, "identity": 0.6210949420928955, "hypothesis": "He comprado 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_Teasing/86e765aec09a0125b2f5f10f3784d1880d63e70a4fc95b2c00ee974782dda738.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "881d9f5ee069ad46134eb867eb3ef36e9f1c2a51e78bf5c1d5b4aa6468d84311", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7496c9fe871a68f50b8857a1d7b46801fd8affb2c04606046267d1b386dc42f7", "generation_seconds_batch": 23.99511252704542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2160775661468506, "target_z": 3.484374961917172, "ce": 6.157639026641846, "genuineness": 4.030367851257324, "identity": 0.3664196729660034, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/881d9f5ee069ad46134eb867eb3ef36e9f1c2a51e78bf5c1d5b4aa6468d84311.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "88d6d425637efa5e4ee8582b55c07ba9b0f356753198bcfd1b43a48e323deae4", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0ad594e89bd3e70860db38cc1e0f6db4c3663a7628a61123ec5628a7ebf261d2", "generation_seconds_batch": 23.424945867969655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7032829523086548, "target_z": 2.5312500207724518, "ce": 6.038498878479004, "genuineness": 4.093128204345703, "identity": 0.48281311988830566, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/88d6d425637efa5e4ee8582b55c07ba9b0f356753198bcfd1b43a48e323deae4.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "88fe7b36214adbed1d43981e96845376a21436d87065466e3100926b75430d21", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "000788347c5109e51d76967201bc71892a1c5ef015aa33827e7705247ecd66cb", "generation_seconds_batch": 17.980288111022674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6608806848526001, "target_z": 0.5937499515309463, "ce": 6.475345611572266, "genuineness": 4.218649387359619, "identity": 0.4810870587825775, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/88fe7b36214adbed1d43981e96845376a21436d87065466e3100926b75430d21.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "8943875b6521cac127f143b23a3f0063f391be7380cb4ad8e86142a639ac6e8e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "13791d5b0e59a0568ffe30fa1c240048059ec23a39f6a99167462d51889cc8c7", "generation_seconds_batch": 24.73094028001651, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1442526578903198, "target_z": 1.4921873978687796, "ce": 6.38003396987915, "genuineness": 4.13078498840332, "identity": 0.2896421551704407, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8943875b6521cac127f143b23a3f0063f391be7380cb4ad8e86142a639ac6e8e.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "8947935e70c1b66c6d30978468d44da155d205eccff0ae508ae42f2724d1dc65", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d6c035e24e202e243186a304309908d09c3495aacd191c445c9a9d62bfdd5361", "generation_seconds_batch": 25.66390287701506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4549221992492676, "target_z": 0.21093748788273659, "ce": 6.1894097328186035, "genuineness": 4.111956596374512, "identity": 0.47689324617385864, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8947935e70c1b66c6d30978468d44da155d205eccff0ae508ae42f2724d1dc65.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "8a2578bd4f535994fb1e311c237c9082e65be3cd58ba1385747968d632eb1a9e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "aad8c3a125cab8c8d78aa4f0821e8469b85b279bc14ed02b9f27a034cd88e2b6", "generation_seconds_batch": 24.435898488969542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6864699125289917, "target_z": 2.4999998338203873, "ce": 6.308549880981445, "genuineness": 4.469690799713135, "identity": 0.6095397472381592, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8a2578bd4f535994fb1e311c237c9082e65be3cd58ba1385747968d632eb1a9e.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": "8a3bbe866d693f18826c9816e9420664f187df9e464d7d9974ba9f90aef4b46a", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c748aa098338a9bf097e1b4158c4b5438ee7dc7e086e4d726a9eaee00f2ac7e8", "generation_seconds_batch": 25.4711670440156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2871626615524292, "target_z": 1.7578124359516076, "ce": 6.340320587158203, "genuineness": 4.093128204345703, "identity": 0.5830820798873901, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Es stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8a3bbe866d693f18826c9816e9420664f187df9e464d7d9974ba9f90aef4b46a.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "8a48bf1a87ccbf3410447d2c68785fdd054a3db081cf6c337aaa912f7f785c8b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3c1e192aab0558d4803269ba513bf7f81b1491e60d8b187b31422da8247eb873", "generation_seconds_batch": 26.689496601000428, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7701648473739624, "target_z": 0.7968750588552795, "ce": 6.09409761428833, "genuineness": 4.532451152801514, "identity": 0.6381404399871826, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8a48bf1a87ccbf3410447d2c68785fdd054a3db081cf6c337aaa912f7f785c8b.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "8b549954394ab350e5cc7c6279e84e194f2b2980a6f765a957f064b483de91d0", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4d255cdd61253a96a00ec882b446524bfb866ad378fccb368748f0a287408a7e", "generation_seconds_batch": 19.796068584080786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.392243504524231, "target_z": 1.9531248857515162, "ce": 6.149696350097656, "genuineness": 3.9173994064331055, "identity": 0.4778560400009155, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8b549954394ab350e5cc7c6279e84e194f2b2980a6f765a957f064b483de91d0.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "8b7aee2175464fd40cf8e47197976314fdad7183c72346217054523d2b481089", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e320f51c2bea9b90ea71807d9b0be20a123406302d8894cc6aa49f6a093f9762", "generation_seconds_batch": 20.01463947596494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.039541721343994, "target_z": 3.1562499930758494, "ce": 6.006728172302246, "genuineness": 4.017816066741943, "identity": 0.5102870464324951, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8b7aee2175464fd40cf8e47197976314fdad7183c72346217054523d2b481089.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "8bebfc0f1829d939ed5f385ea9e6d59fec5ee3363e74a0abccd2d5217d825499", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4dd83cc12cee47a8f3f0159a22fd4518a0c77dabd1de0ff02d12b2e9760e175e", "generation_seconds_batch": 22.852830215007998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3586176633834839, "target_z": 1.8906249549930216, "ce": 6.252951145172119, "genuineness": 3.8671910762786865, "identity": 0.32016944885253906, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8bebfc0f1829d939ed5f385ea9e6d59fec5ee3363e74a0abccd2d5217d825499.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "8c799825f2af6d215ce9cbae30dae92ee85bb556a3fcd0bd1419979615ad9761", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "36c6ac51f07b00a48495bdfb624e9655269c1a6424766044df3316b0ebb22db5", "generation_seconds_batch": 23.373511704965495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6780635118484497, "target_z": 2.484374961917172, "ce": 6.324435234069824, "genuineness": 4.457139015197754, "identity": 0.7663547992706299, "hypothesis": "J'ai trouvé la 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_Teasing/8c799825f2af6d215ce9cbae30dae92ee85bb556a3fcd0bd1419979615ad9761.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "8c8176f569f216fb0c7168b8c7dc6dd8777b5c1d4103ecadf975eec2ea4544fa", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8fa9d0b1be509a3e79e03a9334178e050a8460e91d36f36a634fc3794f7b7afe", "generation_seconds_batch": 27.61587454297114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4048532247543335, "target_z": 1.976562415179156, "ce": 6.523001670837402, "genuineness": 3.6287014484405518, "identity": 0.4610375761985779, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8c8176f569f216fb0c7168b8c7dc6dd8777b5c1d4103ecadf975eec2ea4544fa.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "8c856239619941ea11cd78172fef140e10df9f5166f6d3a44d72da24fa21e0b8", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "fdd60fbe2cb983e97e46accb40cd84807f5dac20b90c1cfbe398ada799717336", "generation_seconds_batch": 23.33181970496662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6612505912780762, "target_z": 2.453124996537925, "ce": 6.260893821716309, "genuineness": 3.998987913131714, "identity": 0.19903497397899628, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8c856239619941ea11cd78172fef140e10df9f5166f6d3a44d72da24fa21e0b8.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "8d1b6c84d8212596bdf597c5e67fc996456c9195ff9e93f82d5da605954e5104", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "403d69632d35122d756fb65a8d5e2ba3b361e51d1b2477a4c42c9c32083bf316", "generation_seconds_batch": 23.1091592409648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.40942645072937, "target_z": 3.843750117710559, "ce": 5.974957466125488, "genuineness": 4.024092197418213, "identity": 0.47824984788894653, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8d1b6c84d8212596bdf597c5e67fc996456c9195ff9e93f82d5da605954e5104.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "8d32c1ecc447b4944ab0e70252192f1110445cca8eff86afb82fedfa292065c5", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "67c8efb785a17fcf4ee9eec3010c8d9da339400362f21fbc1de8f68ed07236e0", "generation_seconds_batch": 24.74447103100829, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7032829523086548, "target_z": 2.5312500207724518, "ce": 6.1894097328186035, "genuineness": 4.080576419830322, "identity": 0.4315789043903351, "hypothesis": "Ik 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_Teasing/8d32c1ecc447b4944ab0e70252192f1110445cca8eff86afb82fedfa292065c5.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "8d7d989c66e57fcf16cc4918703b29efea091192e335ee275dafb397bb89f473", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a655ab9d7ddcc5fd17d9f2825b7af95fca17876f9b7252925cc1eae45fbfc1cd", "generation_seconds_batch": 24.758166885003448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.005915880203247, "target_z": 3.093750062317355, "ce": 6.038498878479004, "genuineness": 4.20609712600708, "identity": 0.5266151428222656, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8d7d989c66e57fcf16cc4918703b29efea091192e335ee275dafb397bb89f473.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "8dc832006157d01c24a4ce8670e511d7a0e0c6f9803da5a31ae8c5889bda2e26", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8cc40f07b1b44b0abc133ecee0a5c7197b09ed7990e07155b21c9647aa495158", "generation_seconds_batch": 17.068793882033788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.19469153881073, "target_z": 1.5859375155793387, "ce": 6.292664527893066, "genuineness": 3.5220088958740234, "identity": 0.39434564113616943, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hin.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8dc832006157d01c24a4ce8670e511d7a0e0c6f9803da5a31ae8c5889bda2e26.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "8dd529142e3d0e40d293dba0929ec637b488a8eed040c0338f24293eb502cf1e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c7156bb07ffe49aeb2ca3981e9d7fb3c40b652ce6d0064a2d09bdfd25a681359", "generation_seconds_batch": 17.579845652915537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.047948122024536, "target_z": 3.1718748649790647, "ce": 6.054384231567383, "genuineness": 3.9299514293670654, "identity": 0.4417080283164978, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8dd529142e3d0e40d293dba0929ec637b488a8eed040c0338f24293eb502cf1e.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "8dfe2b5df3ccd3878b535aca70f0d078605a6311b0d2e7dacc55a7c55ead489f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "14d8a27d7ceedf0596dd39394f380f0c32477afcacdf7558331bf743266fa0c3", "generation_seconds_batch": 17.973106472054496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7806729078292847, "target_z": 0.816406259520707, "ce": 6.4912309646606445, "genuineness": 4.005263805389404, "identity": 0.5444871187210083, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8dfe2b5df3ccd3878b535aca70f0d078605a6311b0d2e7dacc55a7c55ead489f.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "8e2a84b9a3f3bfe4ab89c4dd5be24311966f8405915b5754d40c59ffd61c3309", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "232718bd57351e1bf2dd3cb80113baf9051ea11033fce1b44097a3a52b4e9405", "generation_seconds_batch": 18.129441370954737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5221739411354065, "target_z": 0.33593746018613446, "ce": 6.133810997009277, "genuineness": 4.111956596374512, "identity": 0.8295210599899292, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8e2a84b9a3f3bfe4ab89c4dd5be24311966f8405915b5754d40c59ffd61c3309.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "8e650d929dc7506b70dcd6d529e6d0d06751d1d08b72756ce0a1305f844987be", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0dec6ec1b4774260102fa5d75956326a92ed6ea422389333251386ab7158b134", "generation_seconds_batch": 26.391335221007466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.451088786125183, "target_z": 2.0624998753652903, "ce": 6.157639026641846, "genuineness": 4.293961524963379, "identity": 0.6160489320755005, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8e650d929dc7506b70dcd6d529e6d0d06751d1d08b72756ce0a1305f844987be.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "8ef7d5f9aab245c65df2a0260e641a90f50890bc4739e2b2922459f47ba06c12", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6b2053108e73423a1c36dd5472847d228b44904c6261984de72d52d4eaab30da", "generation_seconds_batch": 24.146205431083217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9803265333175659, "target_z": 1.187499958455097, "ce": 5.95112943649292, "genuineness": 3.7416701316833496, "identity": 0.48243576288223267, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8ef7d5f9aab245c65df2a0260e641a90f50890bc4739e2b2922459f47ba06c12.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "8f5b2844db0f0335a0e39202ccead1e5db893995953ee47fe85545e9375b43a9", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "72f702886dde1a5de3b885a902427cb2f23f0f0a8bec0f6ff623948e96b2cc98", "generation_seconds_batch": 25.270693861995824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.713421106338501, "target_z": 0.6914061764309006, "ce": 6.165581703186035, "genuineness": 4.18726921081543, "identity": 0.6990514993667603, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/8f5b2844db0f0335a0e39202ccead1e5db893995953ee47fe85545e9375b43a9.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": "9007786ed5974674fac8cc3fd9a08ec601eb6fdee34d4a397e087fa0cae3b2d6", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d94573ebb428b0d7e4621bb6e0548c62b00ae56ae6131f32eea92aa5b018d046", "generation_seconds_batch": 24.104121613083407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7974858283996582, "target_z": 0.8476562248999543, "ce": 6.229123115539551, "genuineness": 4.118232727050781, "identity": 0.41633546352386475, "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_Teasing/9007786ed5974674fac8cc3fd9a08ec601eb6fdee34d4a397e087fa0cae3b2d6.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "9089fbffe820de184e25c94e01447c28be55f3001ceb6fecf606b1b7ca9e1a12", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9f3231d1022585694e0c0b2f8bcaccd0c56e71cc2954c66f7e935e7158bda3d8", "generation_seconds_batch": 16.810128369019367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3964468240737915, "target_z": 1.9609375432759408, "ce": 6.181467056274414, "genuineness": 4.281409740447998, "identity": 0.34616994857788086, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/9089fbffe820de184e25c94e01447c28be55f3001ceb6fecf606b1b7ca9e1a12.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": "9180a231d018410904274aca1bc1f84d3aa8c89ee2e7941149f39dcd0c1c7567", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "0041327ff5540e9994359e6d538c358c403c62e7d740596a69da95639a80d2e7", "generation_seconds_batch": 24.745690374984406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5032594203948975, "target_z": 0.3007812768310833, "ce": 6.324435234069824, "genuineness": 4.055472373962402, "identity": 0.5244408845901489, "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": 0.120000000000001, "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_Teasing/9180a231d018410904274aca1bc1f84d3aa8c89ee2e7941149f39dcd0c1c7567.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "91cc4414da11ec416d6c8cd07d92cb82ec626cc55155efc5a268f8ab96a7b660", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "96fc4e16f4c7c8f229540925f5a8a374ed5d0626eb4b731fedc2d0654311e665", "generation_seconds_batch": 24.846673545078374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.602405309677124, "target_z": 2.3437500069241506, "ce": 6.197352409362793, "genuineness": 4.231201171875, "identity": 0.7533994317054749, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/91cc4414da11ec416d6c8cd07d92cb82ec626cc55155efc5a268f8ab96a7b660.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "91dc39f06d39d6f8d0451f6ac4cb240e2b8ef16a667773410b7d73ef330384ea", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a35555cf39b1f62014f9e1042f3921d364ae2107d2f4b6073d1d21722e074192", "generation_seconds_batch": 22.734072212013416, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.30854868888855, "target_z": 3.656249882289441, "ce": 6.332377910614014, "genuineness": 4.306513786315918, "identity": 0.28414386510849, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/91dc39f06d39d6f8d0451f6ac4cb240e2b8ef16a667773410b7d73ef330384ea.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "91ee0d7fa0b70b86a68b6278b16e0d2a2f7565d89dbc89a09cfffaff00a389de", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8b4f06cd3e03e08134199baf600ee4428fe46b589f840aba24c1563e8df8d794", "generation_seconds_batch": 21.085924029001035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5103042125701904, "target_z": 4.031250353131677, "ce": 6.078212261199951, "genuineness": 3.7416701316833496, "identity": 0.377685546875, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/91ee0d7fa0b70b86a68b6278b16e0d2a2f7565d89dbc89a09cfffaff00a389de.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": "92030ba14290012f2081e2e0d743744a6ccae3f8549127fa1a54449986e0b093", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c62771cd9bbe918a4752318343320aaadbdde5454044bfb209a5571743d04cc7", "generation_seconds_batch": 24.104121613083407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.602405309677124, "target_z": 2.3437500069241506, "ce": 6.24500846862793, "genuineness": 4.3127899169921875, "identity": 0.5605910420417786, "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_Teasing/92030ba14290012f2081e2e0d743744a6ccae3f8549127fa1a54449986e0b093.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "9380a6a24c614a123f452b15d239e4e90f8b6c7976ae672dc68190643cc2757f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "23924252025b8a56f8e142a18b4895a7c5d4d1398cf22f1303e49958a17ac4f2", "generation_seconds_batch": 17.413270491058938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5789176225662231, "target_z": 0.4414062318241049, "ce": 6.2767791748046875, "genuineness": 4.231201171875, "identity": 0.3259373903274536, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/9380a6a24c614a123f452b15d239e4e90f8b6c7976ae672dc68190643cc2757f.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "93d3c6050e8e9eabf533117d7a6028d305a6446df7609e1f6e7df6f67b355c5f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f2d0280816aee6c1cea5447c7529b88952184f40c6bb6d4551b35e8a82662568", "generation_seconds_batch": 25.47528666688595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5351535081863403, "target_z": 2.218749923834344, "ce": 6.09409761428833, "genuineness": 3.9801597595214844, "identity": 0.5172369480133057, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/93d3c6050e8e9eabf533117d7a6028d305a6446df7609e1f6e7df6f67b355c5f.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "93d75e3214fc7474d575aa9749c1edc9c6119ec22a695765db2f6985b782c679", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c8bfa38746c8744baaee6197626f4e3d1c6bbe69e4d945b291c6fe4411ca13c0", "generation_seconds_batch": 15.550508777028881, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.636031150817871, "target_z": 2.406249937682645, "ce": 5.792276382446289, "genuineness": 3.490628719329834, "identity": 0.5337839722633362, "hypothesis": "No la puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/93d75e3214fc7474d575aa9749c1edc9c6119ec22a695765db2f6985b782c679.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "93ea9dcdc2ce5652e0da5f80ac9c5d1fc418467cafb0be5774f67dafdef49eb0", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "01f6248b21e6106c45ca799b223f2dbc28e427ee99641f33f7dfc90a0a4f6c93", "generation_seconds_batch": 22.378803233033977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5775558948516846, "target_z": 4.156250214648666, "ce": 5.95112943649292, "genuineness": 4.137060642242432, "identity": 0.7673978209495544, "hypothesis": "De deur staat nog. Opa! Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/93ea9dcdc2ce5652e0da5f80ac9c5d1fc418467cafb0be5774f67dafdef49eb0.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "940759502007ae41960d556c4c00e84c2af1f1c7b6625c194459d724c1a2274b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "fedc88c4fe225e195d082e939b3232fc1549a12ae56d14c423e31e4e0e2c58ea", "generation_seconds_batch": 16.687709343037568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.70921790599823, "target_z": 0.683593740479293, "ce": 6.300607204437256, "genuineness": 4.469690799713135, "identity": 0.5964546799659729, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/940759502007ae41960d556c4c00e84c2af1f1c7b6625c194459d724c1a2274b.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "94c20db7ce685b6d1e8c8762504420bf30a6f2586464ef3cb7181506d530cf97", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "de8f20b93ff51028697e39418fecc6eab93b0adc0856c9f907559dc7fe0463ba", "generation_seconds_batch": 24.910614092019387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8882251977920532, "target_z": 2.8749998615169896, "ce": 5.808161735534668, "genuineness": 3.8546390533447266, "identity": 0.5566058158874512, "hypothesis": "Mi la puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/94c20db7ce685b6d1e8c8762504420bf30a6f2586464ef3cb7181506d530cf97.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "955603bb510ef9ded1c466c9d5ed53b12ab633278353cd011edf1f5dad052b97", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8cffe70ba75e5703f148c7825fb2e3131041e305fc1153910f175b0582e17ffd", "generation_seconds_batch": 16.335963805089705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9971394538879395, "target_z": 1.2187499238343442, "ce": 6.117925643920898, "genuineness": 4.369274139404297, "identity": 0.4340837001800537, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/955603bb510ef9ded1c466c9d5ed53b12ab633278353cd011edf1f5dad052b97.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "95efdba431f593fa78dfa3ae0dcc2d7d5296fbe2bf0fc7db84e999f0be511376", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "4abf57afa3d4e967dfbd0a8e1bd5478e44f102e79bca0658b46f76956a7f6d18", "generation_seconds_batch": 24.50435350195039, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1488258838653564, "target_z": 3.359375100400183, "ce": 6.165581703186035, "genuineness": 3.8922953605651855, "identity": 0.41901087760925293, "hypothesis": "Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereitst.", "wer": 0.15789473684210525, "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_Teasing/95efdba431f593fa78dfa3ae0dcc2d7d5296fbe2bf0fc7db84e999f0be511376.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "95fe828ac463392003edd4393962a75c5a8e06f36b210cd4ed3a2659310905da", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d3c67f6d2214f08b934d4abb63b2c58421ec616ed5a0401133102c1ab1d7820c", "generation_seconds_batch": 24.24869817995932, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0013427734375, "target_z": 1.2265625813587686, "ce": 6.0146708488464355, "genuineness": 4.099404335021973, "identity": 0.5318054556846619, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/95fe828ac463392003edd4393962a75c5a8e06f36b210cd4ed3a2659310905da.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "9619f4c1fffe29e64fa53dbb6cfe63b247655cc27744d1a25f0959ef9d480f02", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "17056a23299f63ad0f9448d72f89bb21d7108f65809475491addb142bc44f924", "generation_seconds_batch": 23.35840481496416, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1067934036254883, "target_z": 3.281249854592839, "ce": 6.23706579208374, "genuineness": 3.936227321624756, "identity": 0.5137669444084167, "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_Teasing/9619f4c1fffe29e64fa53dbb6cfe63b247655cc27744d1a25f0959ef9d480f02.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": "96235b24b53da745b257f7f2eec9dac94a92ff432f06a8c4c0310c52340f1764", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c7d12d35844877cb69dd3628b0a99d7d1bf6d4d22dacc701e1bb3354a3e0c209", "generation_seconds_batch": 19.28190789592918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5687793493270874, "target_z": 2.281249854592839, "ce": 6.443574905395508, "genuineness": 4.055472373962402, "identity": 0.2798137366771698, "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_Teasing/96235b24b53da745b257f7f2eec9dac94a92ff432f06a8c4c0310c52340f1764.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "9630b061ceeaf85b358e05bf52d997a29f0f064035f1e155c4b8aeb349d661a7", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b1439682533252d8de39f0ef2ea6981ccfa8ba7d51dddedf837626710c73d3f1", "generation_seconds_batch": 22.57401869900059, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1568623781204224, "target_z": 1.5156249272964195, "ce": 6.324435234069824, "genuineness": 4.15588903427124, "identity": 0.386234849691391, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/9630b061ceeaf85b358e05bf52d997a29f0f064035f1e155c4b8aeb349d661a7.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "9645be4d23f79c0be8740febccd7762507a570be5da4859d97a569931b5e6c31", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "51226f0a9712f05dc8ebb9561315ed80cd87587c14943a923173af07e873f145", "generation_seconds_batch": 23.49338729295414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6612505912780762, "target_z": 2.453124996537925, "ce": 6.086154937744141, "genuineness": 4.20609712600708, "identity": 0.6372345685958862, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/9645be4d23f79c0be8740febccd7762507a570be5da4859d97a569931b5e6c31.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "969b087f3c18d39faa82ff57d63b8381961f6f1298336e2f513021387c88a76d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "231ef481d88e7975220ea99ca291acf314ca27a09e067a5ddcb482281ecc8e90", "generation_seconds_batch": 23.622062790906057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0643912553787231, "target_z": 1.3437500069241506, "ce": 6.403861999511719, "genuineness": 3.986435890197754, "identity": 0.30609801411628723, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/969b087f3c18d39faa82ff57d63b8381961f6f1298336e2f513021387c88a76d.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "9727d3688c21b6751a8b612f271381bc2b4558420e1d13b32b3958621e884c15", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bb4e79f29ba0f2278ac8ffa8d6d39d2c2dcdf8e367f2cb09b2eb6f4b92c9ebf8", "generation_seconds_batch": 15.550508777028881, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4426823854446411, "target_z": 2.046875003462075, "ce": 5.704906940460205, "genuineness": 3.672633647918701, "identity": 0.20218916237354279, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/9727d3688c21b6751a8b612f271381bc2b4558420e1d13b32b3958621e884c15.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "97814c798955c0442bfcc1111c4fd9f9e3fff9394a3ce08c46cfdab08a4e74a2", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3492c36c7d2592c3baa7b3407e3267da99e03af6ddf746890137bf707acba635", "generation_seconds_batch": 23.212998990085907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5439300537109375, "target_z": 4.093750283890172, "ce": 6.054384231567383, "genuineness": 3.860914945602417, "identity": 0.4113287329673767, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/97814c798955c0442bfcc1111c4fd9f9e3fff9394a3ce08c46cfdab08a4e74a2.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": "97955ab41397bafb2283140d4ce64c372e7ab9dba0710dd40d57d84a8f9098b9", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6edacf7f953087f1eaf1b703e3a60580bdaeff0ec223b03f11aa49ab4ce853a0", "generation_seconds_batch": 24.745690374984406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0517815351486206, "target_z": 1.3203124774965107, "ce": 6.23706579208374, "genuineness": 3.9927117824554443, "identity": 0.5432393550872803, "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_Teasing/97955ab41397bafb2283140d4ce64c372e7ab9dba0710dd40d57d84a8f9098b9.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "979a2182ba922a864f012b3262c7dfe0ba981263eef9c25b14a4f57c2be9afb3", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ceef0f6518cf6a8d483160ef7980e88718f128e72039b7b4cd48b04627a632cd", "generation_seconds_batch": 16.485860008979216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8377864360809326, "target_z": 2.7812499653792475, "ce": 5.855817794799805, "genuineness": 4.099404335021973, "identity": 0.4053211212158203, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/979a2182ba922a864f012b3262c7dfe0ba981263eef9c25b14a4f57c2be9afb3.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "97b4ea49543f88e2cb3dd7d2824c600d2716940a38a99f95920d6e9df4396ca6", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f33c683e22edfd35e8a80439415d55740d5e1b99f9a14b0e8636ca00feecfee7", "generation_seconds_batch": 23.83314279804472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7827745079994202, "target_z": 0.8203124774965108, "ce": 6.395919322967529, "genuineness": 4.3504462242126465, "identity": 0.3999771475791931, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/97b4ea49543f88e2cb3dd7d2824c600d2716940a38a99f95920d6e9df4396ca6.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "9814f8370cb06328db61986e07b6ca172bf6a6798578ad518c97498734d3d5e0", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "bb9f3567ee6770ff8de6dfe6e88e3e6295f31c68e2c87dc15a46e9cbf222e503", "generation_seconds_batch": 25.345221993979067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6612505912780762, "target_z": 2.453124996537925, "ce": 6.213237762451172, "genuineness": 4.030367851257324, "identity": 0.5058941841125488, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "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_Teasing/9814f8370cb06328db61986e07b6ca172bf6a6798578ad518c97498734d3d5e0.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "983f4c15bb1b654046f29fe75eadac52498c7b108f457e3a8cce347813610b61", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0185dc1b98b515a46c203b7682a0fc04a4c2331f46947479d3c795e3ec656bae", "generation_seconds_batch": 23.49338729295414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.375800609588623, "target_z": 3.781250186952064, "ce": 6.24500846862793, "genuineness": 4.281409740447998, "identity": 0.6134709715843201, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/983f4c15bb1b654046f29fe75eadac52498c7b108f457e3a8cce347813610b61.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "c19c245eca51cc700abe0b5d0add64aaf91469ab29a5499ce0e7fc059176aafc", "generation_seconds_batch": 17.23954866209533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6419661641120911, "target_z": 0.5585937681758951, "ce": 6.41180419921875, "genuineness": 4.7332844734191895, "identity": 0.6642686724662781, "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_Teasing/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "99d6255125f41c3eaa255b2cf6742bc8bfb01758da084e1af99bf401da6dcb9b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "025a0ed20e1f200eb4267f5f5d551e31b7be5d0da169015dd04733230edfe730", "generation_seconds_batch": 24.04424065502826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9638835191726685, "target_z": 3.015625038082828, "ce": 6.173524379730225, "genuineness": 3.9676074981689453, "identity": 0.559364378452301, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que.", "wer": 0.11764705882352941, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/99d6255125f41c3eaa255b2cf6742bc8bfb01758da084e1af99bf401da6dcb9b.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "9abe61820914676650163d5914ed8611f64298b3f2301dce1ac53f979bba2fec", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "372d4ce64fb938d5460d0c0d6ae09f842bdf891b207f27cba8bacc7e538b5164", "generation_seconds_batch": 17.788995668990538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1526591777801514, "target_z": 1.5078124913448119, "ce": 6.133810997009277, "genuineness": 4.061748504638672, "identity": 0.5953585505485535, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/9abe61820914676650163d5914ed8611f64298b3f2301dce1ac53f979bba2fec.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "9b22ffbad089555679eabf8213a7df6fc1630930606a13b58e1f7acf109e64bb", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1692540ffb0971d0e079cbe7a4748216a5952a4e44a8600323e3a6b857bfbbff", "generation_seconds_batch": 21.85174590605311, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3376015424728394, "target_z": 1.8515625536621665, "ce": 6.260893821716309, "genuineness": 3.6977379322052, "identity": 0.38213181495666504, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/9b22ffbad089555679eabf8213a7df6fc1630930606a13b58e1f7acf109e64bb.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "9b4f1ccb9608bd1fffb30331e625504e57080ddd2bd5c677954fc79cd4c60ddd", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "473ca919a06caf38e9209ddfe31b3c47d1c80ca50392777a320720a7c9c8261d", "generation_seconds_batch": 23.852204752038233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.829379916191101, "target_z": 2.7656248719032153, "ce": 5.998785495758057, "genuineness": 4.375550270080566, "identity": 0.5415228009223938, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/9b4f1ccb9608bd1fffb30331e625504e57080ddd2bd5c677954fc79cd4c60ddd.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "9c026f871a163ab39640d539bf1eabd0304d22c73baa9d5722a2023384364dda", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "67730e7439f5a0c52a1b013ad1b6b5c16e3f65a008c263994bdb1e07f3e21d5d", "generation_seconds_batch": 24.482426592963748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7453153133392334, "target_z": 2.6093750450069786, "ce": 6.372091293334961, "genuineness": 3.6789097785949707, "identity": 0.5724656581878662, "hypothesis": "Ich habe die kleine Schacht gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/9c026f871a163ab39640d539bf1eabd0304d22c73baa9d5722a2023384364dda.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7d407b613a72e8af03edf59a066c7e72dd07532d55f4e9c76e2b9c197de630ff", "generation_seconds_batch": 18.245699661085382, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4160422682762146, "target_z": 0.13867184600511967, "ce": 6.356205940246582, "genuineness": 4.375550270080566, "identity": 0.4665166139602661, "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_Teasing/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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "ef91b60fb93ac5bf4b6a405f2e637a067be107e562e823cbcdca52245680d137", "generation_seconds_batch": 19.183410948957317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1249682754278183, "target_z": -0.40234374740344353, "ce": 6.300607204437256, "genuineness": 4.457139015197754, "identity": 0.49437415599823, "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_Teasing/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "9ca0be74e48a65d9449efaab05c8505f3f9661808ab4ba05bd749b3705d2630d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "666e8345a40c04d928319d722538e60965feb4d3ab636a1ca5f92ccec00225b1", "generation_seconds_batch": 26.663519599009305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8458230495452881, "target_z": 0.9375000138483011, "ce": 6.117925643920898, "genuineness": 4.080576419830322, "identity": 0.5433139204978943, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/9ca0be74e48a65d9449efaab05c8505f3f9661808ab4ba05bd749b3705d2630d.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": "9d4c416575cddb8d9617b10dbeb381281663c00364b050ee0835b8804c0afca8", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5d4db5d57b9a3d77a6af5ed66c2dd7d53218c0dfddbec98a8c9951ca0f82e522", "generation_seconds_batch": 17.465365809039213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2328906059265137, "target_z": 3.5156251488692365, "ce": 6.324435234069824, "genuineness": 4.18726921081543, "identity": 0.6319711208343506, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/9d4c416575cddb8d9617b10dbeb381281663c00364b050ee0835b8804c0afca8.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": "9d4efb6c56139a2215bd09f28b2ffb047983771aa425d1940d276fe65c2faa6d", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "91fab2973e5344ba54a68908b9a98d031f013710eca7ae5f47a297c5af3a5e59", "generation_seconds_batch": 16.098751422017813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3796337842941284, "target_z": 1.9296873563238766, "ce": 6.086154937744141, "genuineness": 4.080576419830322, "identity": 0.6293398141860962, "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_Teasing/9d4efb6c56139a2215bd09f28b2ffb047983771aa425d1940d276fe65c2faa6d.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "9d89bfa6e1f329a554442b58991abd056d5adaca3d674be51c80ed73cdc5838a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "40e37f944900daa5e679e0012e2011bf0a650d4e4980d847b668fd9bd3a72263", "generation_seconds_batch": 26.391335221007466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7285022735595703, "target_z": 2.578124858054914, "ce": 6.006728172302246, "genuineness": 3.9676074981689453, "identity": 0.656402587890625, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/9d89bfa6e1f329a554442b58991abd056d5adaca3d674be51c80ed73cdc5838a.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "9eebb238477522ac8ed40dafff272ca94902a02224830dcd69a7d33de7aac890", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6d4c2d17f6e0fdb1488cb819c4ba33133bacbbb8a40e65e1016e8a0c29e22cf5", "generation_seconds_batch": 24.74447103100829, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1488258838653564, "target_z": 3.359375100400183, "ce": 6.006728172302246, "genuineness": 3.8671910762786865, "identity": 0.15841080248355865, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen daar samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/9eebb238477522ac8ed40dafff272ca94902a02224830dcd69a7d33de7aac890.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "9f5910b8a9fdcc64edf3e1bf503880fef95246c663400af196feaea9b83c6e5e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "02b2eb60cf3c3feb92110b1ae0d23891bb43893b4dca181df96bc9c8ce6789d6", "generation_seconds_batch": 27.61587454297114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4594953060150146, "target_z": 2.0781249688413226, "ce": 6.300607204437256, "genuineness": 3.8044304847717285, "identity": 0.44664615392684937, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/9f5910b8a9fdcc64edf3e1bf503880fef95246c663400af196feaea9b83c6e5e.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "9fb42735db3f1d293304144a9e4f79adddb98f54870e690417444da931bfd807", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e5b11172daec093c8e57287795a5aa2376177c43d68816a366a7c42f054f5ebe", "generation_seconds_batch": 23.792501399992034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6780635118484497, "target_z": 2.484374961917172, "ce": 6.2767791748046875, "genuineness": 3.986435890197754, "identity": 0.17031164467334747, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/9fb42735db3f1d293304144a9e4f79adddb98f54870e690417444da931bfd807.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "9fe81ca22ba5d260b38cb02460cd09db174a7b4d7a0bc70984592bd88d8336c8", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1ecbd7e335a29002436ceccbcc0bd10608600033510e06d11541c6a11ff92e4c", "generation_seconds_batch": 24.081009836983867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5183405876159668, "target_z": 2.187499958455097, "ce": 6.300607204437256, "genuineness": 3.823258876800537, "identity": 0.31870076060295105, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/9fe81ca22ba5d260b38cb02460cd09db174a7b4d7a0bc70984592bd88d8336c8.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "a01b0aa513a93638737156bd1a2d2ca343e59b894983f7272555323447e87030", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1c2f17e73579e82ec5e7be3721aae575591c4ae52d2b25529e6a58581f56c20a", "generation_seconds_batch": 15.340113712009043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1740453243255615, "target_z": 3.406250159255462, "ce": 6.149696350097656, "genuineness": 3.653805732727051, "identity": 0.23089240491390228, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a01b0aa513a93638737156bd1a2d2ca343e59b894983f7272555323447e87030.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "a024f693cdd89098830a288cdfbe0f630784db3dda73c45c86fee4eedda16c2d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c291a92c285f96f28c9faafd46f49625f70fafa7f2e69c364585338f69f56f3e", "generation_seconds_batch": 18.2316890549846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.198894739151001, "target_z": 1.5937499515309463, "ce": 5.95112943649292, "genuineness": 4.074300289154053, "identity": 0.7778483033180237, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a024f693cdd89098830a288cdfbe0f630784db3dda73c45c86fee4eedda16c2d.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "a098d5a55521569a864d47ac04d84f9a2b220a9bb6fd95bd8f424adf24ff398a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "fb506f750e066e9886ca4915ed5c7c295e24b42fec27d2109c3ed58e07d6e5f5", "generation_seconds_batch": 17.788995668990538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8377864360809326, "target_z": 2.7812499653792475, "ce": 6.205295085906982, "genuineness": 4.2374773025512695, "identity": 0.7353264093399048, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a098d5a55521569a864d47ac04d84f9a2b220a9bb6fd95bd8f424adf24ff398a.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "a0dff2bb55c834af2e605b4f2863116b3c538adcfa970fbde5d37abdc6c826dd", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0dfd2ae6c425c85ee35269ad9f0a2f560f888795ebf08bc47346a59b7effd0dc", "generation_seconds_batch": 27.162357995985076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0896106958389282, "target_z": 1.3906250657794301, "ce": 6.078212261199951, "genuineness": 4.2249250411987305, "identity": 0.4840323328971863, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a0dff2bb55c834af2e605b4f2863116b3c538adcfa970fbde5d37abdc6c826dd.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": "a0ed571d6de7c9e1e6ec21f577b7dedbffecb9163eee135144eaa176945b0d7a", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3a66e0c2d0180d01e07cbd8c9c80c4beff26510e2e2e93fcbead0f525e2f20e3", "generation_seconds_batch": 24.478578449925408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.602405309677124, "target_z": 2.3437500069241506, "ce": 6.149696350097656, "genuineness": 4.137060642242432, "identity": 0.5336506962776184, "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_Teasing/a0ed571d6de7c9e1e6ec21f577b7dedbffecb9163eee135144eaa176945b0d7a.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "a0fcc95df10debc1c61645efa181ab6f5b4d35d85a230a65d6db9bb5e15184b8", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4d5af1aaa535da45e8728011d621c75fdef452eac3267eb536fc209c776ace07", "generation_seconds_batch": 21.85174590605311, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7453153133392334, "target_z": 2.6093750450069786, "ce": 6.308549880981445, "genuineness": 3.9801597595214844, "identity": 0.39022302627563477, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a0fcc95df10debc1c61645efa181ab6f5b4d35d85a230a65d6db9bb5e15184b8.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "a22a49735e1d5336bd7d1da2f07ba5ce7e19ca844a2a500e4eac13269a61bdd6", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "60171b098af55cc1c14e84f0b74a9343ec4e94d041bddc9bd07b469146bad259", "generation_seconds_batch": 19.25151489698328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9722899198532104, "target_z": 3.0312499099860433, "ce": 6.181467056274414, "genuineness": 4.3127899169921875, "identity": 0.6704414486885071, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble what", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a22a49735e1d5336bd7d1da2f07ba5ce7e19ca844a2a500e4eac13269a61bdd6.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": "a23cbf4b341a8f4b2123cb9950e499fab516fe8b713831a46a9c9451c5f336d8", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d9181e7529d3804f69c52cf2127bd63ccddb14b83edc005fb9aa73ff17987eb2", "generation_seconds_batch": 15.291657591005787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9635136127471924, "target_z": 1.1562499930758494, "ce": 6.205295085906982, "genuineness": 4.306513786315918, "identity": 0.7328923940658569, "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_Teasing/a23cbf4b341a8f4b2123cb9950e499fab516fe8b713831a46a9c9451c5f336d8.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "a2802b89ae33162fdea279fbb0390cd8c3395f30af1fdb8d28b20a7a1d8f5c77", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b6cc7a7c9aa95e8af1b01a515e2e3eb35470be4678b4a82d9a055c255cb518ee", "generation_seconds_batch": 16.66378880001139, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7155227661132812, "target_z": 0.6953125051931129, "ce": 6.252951145172119, "genuineness": 4.306513786315918, "identity": 0.7233700752258301, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a2802b89ae33162fdea279fbb0390cd8c3395f30af1fdb8d28b20a7a1d8f5c77.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "a29ae1d63afe9b2d9a538e45c7452fef1359e1371af95b425e032e4b1be596d2", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "46e9783c3dc4a6b4f7713ef5885f2dc83b9025d17afef6a8e30da6a96090d497", "generation_seconds_batch": 24.739486913895234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40422070026397705, "target_z": 0.11669924525651375, "ce": 6.221180438995361, "genuineness": 4.419482707977295, "identity": 0.6162528991699219, "hypothesis": "J'ai trouvé la 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_Teasing/a29ae1d63afe9b2d9a538e45c7452fef1359e1371af95b425e032e4b1be596d2.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "a3379a7179f505ca5eadcd7b646d0339e77e2670ae6a401352e80734e67a7bad", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e1210be7d06c1f43619c46c37c31befdfba301ac1b54416228a727e834c431d2", "generation_seconds_batch": 28.005812659976073, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26104801893234253, "target_z": -0.14941402852838648, "ce": 5.967014789581299, "genuineness": 4.093128204345703, "identity": 0.538719892501831, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a3379a7179f505ca5eadcd7b646d0339e77e2670ae6a401352e80734e67a7bad.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "a37c36d6303535c4874a3b0894b6f2852153a61f453f3fcf6e3a384fd7be3d34", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f78d36d6da9f836d31ed1f825bb65e1627a895042131345ea05aa067de3057be", "generation_seconds_batch": 25.88108492398169, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7285022735595703, "target_z": 2.578124858054914, "ce": 6.435632705688477, "genuineness": 4.118232727050781, "identity": 0.5454553365707397, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a37c36d6303535c4874a3b0894b6f2852153a61f453f3fcf6e3a384fd7be3d34.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "a38a1680b692861a587f67f41a6de4901423f8ccbcdd9a7f2ef1abc7013d6208", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c636d69a4326dc1f02782366b4d47f927a4517f4e18e11e3e55214e064963232", "generation_seconds_batch": 24.482426592963748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.505361020565033, "target_z": 0.3046874948068871, "ce": 6.324435234069824, "genuineness": 3.8671910762786865, "identity": 0.5518192052841187, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a38a1680b692861a587f67f41a6de4901423f8ccbcdd9a7f2ef1abc7013d6208.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "a3dbf9c17cbb9a092f9e03aa0f8e08f78d8c985b524d8d34c9b134c661bf15fb", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c37ad0fd8b590cc7d30a206ba8bd05d878896fd34560bfbba12b119a3115ac32", "generation_seconds_batch": 21.768442295957357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9218511581420898, "target_z": 2.937500013848301, "ce": 5.831989288330078, "genuineness": 3.835810661315918, "identity": 0.6257436275482178, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a3dbf9c17cbb9a092f9e03aa0f8e08f78d8c985b524d8d34c9b134c661bf15fb.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "a4395e332c5fd0de00e17b324bbd86981df12c85457dae3e8ba80f0f46d52923", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "81e30af2708911febb4498408f095beebb946c2c8bc4a2f7f35e00b7eebf8fab", "generation_seconds_batch": 23.774357768008485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2409271001815796, "target_z": 1.6718749757654732, "ce": 6.41180419921875, "genuineness": 3.8671910762786865, "identity": 0.22712020576000214, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a4395e332c5fd0de00e17b324bbd86981df12c85457dae3e8ba80f0f46d52923.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "a4450902e9f79a91d9dea146ba4d73131ea4997776a30d0f3db288064107dd13", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "52996124d7be9c4555cdb82499b1a202388cc7862120ca2fc72f3d641c29f1ee", "generation_seconds_batch": 25.34324284410104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4679017066955566, "target_z": 2.093749840744538, "ce": 6.181467056274414, "genuineness": 4.2751336097717285, "identity": 0.302817702293396, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a4450902e9f79a91d9dea146ba4d73131ea4997776a30d0f3db288064107dd13.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "a4929187189be6ecea85ab4ae6ca890e46ec51b0f3e991086be9cfb07bddb849", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a4c93f6924c9863205c90ff9ae80c65f005dc77e1f75ac0f8ddd5509d4970592", "generation_seconds_batch": 23.53850200190209, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8630058765411377, "target_z": 2.828125024234527, "ce": 6.221180438995361, "genuineness": 4.149612903594971, "identity": 0.6271238327026367, "hypothesis": "Oh, j'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a4929187189be6ecea85ab4ae6ca890e46ec51b0f3e991086be9cfb07bddb849.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "a497adc441e30bb5d5ae49751e4e7b64a642267247bc620e373b7492f6dd2af4", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c5c2f100e456e611a1d8733bcb6f36734a576cee439bcdc22382a4089f53f716", "generation_seconds_batch": 23.04378169903066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7453153133392334, "target_z": 2.6093750450069786, "ce": 6.054384231567383, "genuineness": 3.886019229888916, "identity": 0.4874063730239868, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. 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_Teasing/a497adc441e30bb5d5ae49751e4e7b64a642267247bc620e373b7492f6dd2af4.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": "a4c847a30ae8ba127bef14590d512bdd9e5734f0710553bc7ad5a403836d6619", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6cd6b109113d7b96f11961883d4c6f1f80ef25a8676eef8c38dc4ef2a9bb310b", "generation_seconds_batch": 22.235955324023962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7032829523086548, "target_z": 2.5312500207724518, "ce": 6.125868320465088, "genuineness": 4.099404335021973, "identity": 0.5184494256973267, "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_Teasing/a4c847a30ae8ba127bef14590d512bdd9e5734f0710553bc7ad5a403836d6619.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "a4cb7aed0617c488db235010c3d49641272eb381ad051841c1fa47a6b441f121", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "23a3cf9ea39eb42cb7d64f2d8a7ef8db0c97c6e7fdd82055c8a952ef87b9bc39", "generation_seconds_batch": 23.838571652886458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48224323987960815, "target_z": 0.2617187647138199, "ce": 6.435632705688477, "genuineness": 4.20609712600708, "identity": 0.654049277305603, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a4cb7aed0617c488db235010c3d49641272eb381ad051841c1fa47a6b441f121.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "a4da03122c7d9ccb530dc8d417128bddbfc0a76e8123699b5484b60ea1eabe53", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "60f1554345b35bfbd6a1915b43aad69d6130ee7a8ec681925807ca0d794dd307", "generation_seconds_batch": 24.146205431083217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5435600280761719, "target_z": 2.2343750173103762, "ce": 5.796247482299805, "genuineness": 3.798154592514038, "identity": 0.5357145667076111, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a4da03122c7d9ccb530dc8d417128bddbfc0a76e8123699b5484b60ea1eabe53.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "a4e7cab806bf11f729dd211624a620289a279b6a802b6fc6c7d898a2bb623cf1", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "72700f68af4864bb0f2095ab334181046db44e701a8a46df0e88238f2827405f", "generation_seconds_batch": 25.06631649506744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.009749174118042, "target_z": 1.2421874532619839, "ce": 5.9431867599487305, "genuineness": 3.8044304847717285, "identity": 0.42750829458236694, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a4e7cab806bf11f729dd211624a620289a279b6a802b6fc6c7d898a2bb623cf1.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "a5b76111c0d7419455a6df6c0682ee29770159d0ce5029fad7e96aedff888540", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a6fcb67b62c49717d2989db9be7ca49fc03fecc4e54e64415da3ec849e102643", "generation_seconds_batch": 19.219456227030605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.034968614578247, "target_z": 1.2890625121172634, "ce": 6.546830177307129, "genuineness": 3.9425034523010254, "identity": 0.44152048230171204, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a5b76111c0d7419455a6df6c0682ee29770159d0ce5029fad7e96aedff888540.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "a5ef025d1e52f5dd12d9cf72c69df82d60a35fdb2e24b9b31bd777baeefe397c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "61c678889233ae97eb0830529c24c98ee4284d25f4cc99e342a793572d7d8f74", "generation_seconds_batch": 17.57026849698741, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0983870029449463, "target_z": 3.2656249826896238, "ce": 5.95112943649292, "genuineness": 3.8420867919921875, "identity": 0.2933265268802643, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a5ef025d1e52f5dd12d9cf72c69df82d60a35fdb2e24b9b31bd777baeefe397c.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "a6204ee5b2f9c0fadcf0f3e65472b13de54e56ccd696d514ef7bac58f1abba5f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f619a203a24c69c63a148694a768ed0251cdfad50508da87b19395645125c41d", "generation_seconds_batch": 22.367336611961946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7369087934494019, "target_z": 2.5937499515309463, "ce": 5.9431867599487305, "genuineness": 3.8044304847717285, "identity": 0.2614764869213104, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a6204ee5b2f9c0fadcf0f3e65472b13de54e56ccd696d514ef7bac58f1abba5f.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "a6cf3a06b3db0f7745fb9c61e6b724075f075bc573c7318eab4446554b156e82", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7be4e9b27416f9c06c2ee570f4b846537b7db572ace645a5d338fdbd9c14e209", "generation_seconds_batch": 23.114872189005837, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.695246458053589, "target_z": 4.375000193876215, "ce": 5.982900142669678, "genuineness": 4.105680465698242, "identity": 0.6631821393966675, "hypothesis": "De er staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a6cf3a06b3db0f7745fb9c61e6b724075f075bc573c7318eab4446554b156e82.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "a88091c4606a4bef0cb47b9b3678785e4395bcbfd8cb65a6ee3c63d36bd71027", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8c7306fab47718cdcb295142a761322224ba74d0e7350219a8e14f00770bec37", "generation_seconds_batch": 24.13441788207274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6528440713882446, "target_z": 2.4374999030618927, "ce": 6.24500846862793, "genuineness": 4.293961524963379, "identity": 0.7552204132080078, "hypothesis": "J'ai trouvé la petite boite. Elle était prêt de la vie fenêtre. We've regarded ensemble what contien?", "wer": 0.47368421052631576, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a88091c4606a4bef0cb47b9b3678785e4395bcbfd8cb65a6ee3c63d36bd71027.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "b613a182cc6f1528fc04289eb3b82ae422727293fdb14ab591b3bcd6e82c479e", "generation_seconds_batch": 18.123831278993748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030395478010177612, "target_z": -0.5781250242345268, "ce": 6.197352409362793, "genuineness": 4.055472373962402, "identity": 0.5117148160934448, "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_Teasing/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "a8e6bf6a35e30ef60c2674611796d123cc5ac02b687a24949b9faae66c075245", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7a53a3eb0669d65b4f4226f4751c48437213170a2f8cb3f232ddb7d3f9ca621b", "generation_seconds_batch": 23.373511704965495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.636031150817871, "target_z": 2.406249937682645, "ce": 6.173524379730225, "genuineness": 4.2374773025512695, "identity": 0.5942980051040649, "hypothesis": "Et tu sais, j'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.15789473684210525, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a8e6bf6a35e30ef60c2674611796d123cc5ac02b687a24949b9faae66c075245.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "a90bc9cc6c5ae2e68c4d0a0b4e821034b75d76e6169696eacfbb7c18bf943b85", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d621e76bb4e8775ee4429b736407b4605737c54bcdbac958b6ac04bd8afe20cc", "generation_seconds_batch": 24.478151728981175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5841716527938843, "target_z": 0.4511718321568186, "ce": 6.157639026641846, "genuineness": 4.394378662109375, "identity": 0.6595162749290466, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a90bc9cc6c5ae2e68c4d0a0b4e821034b75d76e6169696eacfbb7c18bf943b85.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "a922daeb63aad1deab8c1da65b2b2cc53b5fdafd3f4afe0f27df5b4be117d89e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d1b7708e03d85db081f6ed750cd867c0f162e608dfebf56cf6f257f1eb6cee8a", "generation_seconds_batch": 23.841643725987524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8798187971115112, "target_z": 2.8593749896137743, "ce": 6.252951145172119, "genuineness": 3.998987913131714, "identity": 0.3209952116012573, "hypothesis": "I found little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/a922daeb63aad1deab8c1da65b2b2cc53b5fdafd3f4afe0f27df5b4be117d89e.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "9773ebde533e22e2864172c58b1c8fb7d300788cce3ec7d0452f987de702873c", "generation_seconds_batch": 18.267638348974288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19852487742900848, "target_z": -0.26562501038622577, "ce": 6.252951145172119, "genuineness": 4.557555198669434, "identity": 0.6452248096466064, "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_Teasing/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "aa6a302a4ceb4a5fa7f00775862f2a0e27f0e16e1f5c21e13171f05ff689185f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e241f3589bb7690c753ef595d18737e5fe3c3ddd281a6e2215ae189bfc7031cb", "generation_seconds_batch": 23.428753401967697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7029130458831787, "target_z": 0.6718749757654732, "ce": 6.427689552307129, "genuineness": 4.632867813110352, "identity": 0.5772611498832703, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/aa6a302a4ceb4a5fa7f00775862f2a0e27f0e16e1f5c21e13171f05ff689185f.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "aa6c2dc1cacebb5aeb17f56aa44285e0efeeff5eec123c82e72572ca6ce1553b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "97fd355f6332ecd0db599d64022f54d15780bd9d0c50edf1d5b75a203fed6d72", "generation_seconds_batch": 23.79222538403701, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.577185869216919, "target_z": 2.296874948068871, "ce": 6.054384231567383, "genuineness": 4.231201171875, "identity": 0.5467283725738525, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/aa6c2dc1cacebb5aeb17f56aa44285e0efeeff5eec123c82e72572ca6ce1553b.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "aa9685324649e8d02693393b031bfe2f81e2481b4e87beb4657c30dcbe80ecbb", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "94596273e566df50f2a2a83a9c815973535dd3b4fefcc21d3f28a8f5d82a449b", "generation_seconds_batch": 18.919154611998238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.820973515510559, "target_z": 2.75, "ce": 6.229123115539551, "genuineness": 3.936227321624756, "identity": 0.3104654848575592, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/aa9685324649e8d02693393b031bfe2f81e2481b4e87beb4657c30dcbe80ecbb.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "aa9f45b4062d08155f6a064268046a25764ad6516f52a2b82d4fade3ccc63e2c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "754c88e0fbb26077bd30ea36d176d4a123f6acc1d89f2a180e7ab02dc677bd8d", "generation_seconds_batch": 22.763406035024673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.228317379951477, "target_z": 1.6484374463378335, "ce": 6.197352409362793, "genuineness": 3.936227321624756, "identity": 0.36439749598503113, "hypothesis": "Ich habe die kleine Schacht gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.125, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/aa9f45b4062d08155f6a064268046a25764ad6516f52a2b82d4fade3ccc63e2c.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "aac02e08a90cc26a52c431f0143018994492f3bc8d9507ac33c877bc80924969", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "90dda474a73544b7ad97657a930a303361aff356d744a66319800221652a791a", "generation_seconds_batch": 17.41001522995066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8714122772216797, "target_z": 2.843749896137742, "ce": 6.213237762451172, "genuineness": 3.936227321624756, "identity": 0.4735608696937561, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/aac02e08a90cc26a52c431f0143018994492f3bc8d9507ac33c877bc80924969.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "aae74b81d559628efe4aef5f54c49405b790d386bb2e3c14c4f0df2511c9e014", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f4d2e274d809f7863e77f4cf2a7deac941e19e9f9f84f7f1404c2bf647ff6e9d", "generation_seconds_batch": 20.807573211030103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.02272891998291, "target_z": 3.125000249269419, "ce": 6.229123115539551, "genuineness": 4.143336772918701, "identity": 0.48954373598098755, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/aae74b81d559628efe4aef5f54c49405b790d386bb2e3c14c4f0df2511c9e014.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "aaf51523e874b30210ebb6048b4979870b368bf625f283d7a31a24277cc2f882", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2b14c84bf9ca3c150ca5ff4a0df8ec32ba1de69793ffe0fe0cf7d5b4c6e4e182", "generation_seconds_batch": 23.936593572958373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1022204160690308, "target_z": 1.4140625952070698, "ce": 6.348263263702393, "genuineness": 4.13078498840332, "identity": 0.31634825468063354, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/aaf51523e874b30210ebb6048b4979870b368bf625f283d7a31a24277cc2f882.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "314bb4663269ccd40c51a5bb702328f09c83a5d8586978cba2a7b9ad414b19b2", "generation_seconds_batch": 16.87453493999783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07242783904075623, "target_z": -0.5, "ce": 6.403861999511719, "genuineness": 4.262581825256348, "identity": 0.41787198185920715, "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_Teasing/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "abf5d1216f807f900f5f1c5eae5c111f620ace4c97536debcce2e158008cd445", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0c1ec9cb32845fea6f00824d17ee3964baac586b35e301a1ea0e458bfac6bf05", "generation_seconds_batch": 16.31573352299165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8461928367614746, "target_z": 2.7968748372824628, "ce": 5.696964263916016, "genuineness": 3.7040140628814697, "identity": 0.5444406270980835, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/abf5d1216f807f900f5f1c5eae5c111f620ace4c97536debcce2e158008cd445.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "ac376f332639885c5eb2ba2de8eeb0a44287e86006bf64e8e1b0bd99ebb14823", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4bc5a3a247b5cab3b740fe7613ed0139df5027bc8e3929ad649152d84a8e0139", "generation_seconds_batch": 26.928479771944694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3198933005332947, "target_z": -0.04003903891461226, "ce": 6.1020402908325195, "genuineness": 4.287685871124268, "identity": 0.7757510542869568, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ac376f332639885c5eb2ba2de8eeb0a44287e86006bf64e8e1b0bd99ebb14823.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "ac564d88edc479ccfef753c085a4c6163f1f41e4c65bb32a2014a58edfbd2aa8", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e886fda9de7e49669d6153d4822082fe62b7f070162575cbd499383e20736a6c", "generation_seconds_batch": 18.831280810991302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5519664287567139, "target_z": 2.2499998892135915, "ce": 6.1894097328186035, "genuineness": 4.231201171875, "identity": 0.6027634143829346, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ac564d88edc479ccfef753c085a4c6163f1f41e4c65bb32a2014a58edfbd2aa8.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": "ac691695101dc95b461ca88f8b7dbe858b0517550ac03fe968e3d8ad05fe4a73", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ee216d8e9289c6778e39cd28d42f13709d4edb6a58ae6e5e5524aba292956829", "generation_seconds_batch": 17.93444585602265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38609424233436584, "target_z": 0.08300782440088372, "ce": 6.38003396987915, "genuineness": 4.036643981933594, "identity": 0.32401931285858154, "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_Teasing/ac691695101dc95b461ca88f8b7dbe858b0517550ac03fe968e3d8ad05fe4a73.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "ad246612052be3f85d8af524f4e7b38ab5f8ce61e05dd4afb6c74bb4c8c644f1", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "88a670cb33456db4d6253c0d89ef9a933c850261d41a5998a5111875a2c407c1", "generation_seconds_batch": 22.963030923972838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.443052291870117, "target_z": 3.9062500484690537, "ce": 6.316492557525635, "genuineness": 4.18726921081543, "identity": 0.5409197211265564, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ad246612052be3f85d8af524f4e7b38ab5f8ce61e05dd4afb6c74bb4c8c644f1.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3dc83eec2143ae176989a3b35a3605486c2f791780bb115e06e25cd887cfdf50", "generation_seconds_batch": 19.7487087569898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3075462877750397, "target_z": -0.06298827724697548, "ce": 6.181467056274414, "genuineness": 4.319066047668457, "identity": 0.4008106589317322, "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_Teasing/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": "adfaed65c93c721f97f929b11a696ae20a4b8d3c40dceaec6b51d580c2d87ce0", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b418f70fc61b0bfb533e9772cdb4598b40dda6ee85d9d52cb33e3bf8ac2329dc", "generation_seconds_batch": 22.39494717400521, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1568623781204224, "target_z": 1.5156249272964195, "ce": 6.205295085906982, "genuineness": 4.18099308013916, "identity": 0.6485747694969177, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekkast. We zetten het na de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/adfaed65c93c721f97f929b11a696ae20a4b8d3c40dceaec6b51d580c2d87ce0.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "ae24049b6795595beac2545f4c066370fd45b3effeba6de2957e2e5b5366c65c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d6b222ea3d02637f3a673f6e074ef31d8eeae31381d6dbcf756377fbc0277d19", "generation_seconds_batch": 23.939425475895405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5603729486465454, "target_z": 2.2656249826896238, "ce": 6.054384231567383, "genuineness": 4.042920112609863, "identity": 0.3489931523799896, "hypothesis": "Ik 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_Teasing/ae24049b6795595beac2545f4c066370fd45b3effeba6de2957e2e5b5366c65c.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "df8291cf1b625152f95498d11e30c95209d0a817c5d5f1a136d485cd37ecead5", "generation_seconds_batch": 16.264178700046614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08293592929840088, "target_z": -0.4804687439413683, "ce": 6.300607204437256, "genuineness": 3.898571252822876, "identity": 0.40671220421791077, "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_Teasing/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "af28426495157d0b07221275f2596e2821c791ead29f329cd97b22ecfdbfb66b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "61b520442cdd0230d006517691480a090d87dd8f93fc37bf89ca005d95b01857", "generation_seconds_batch": 22.723982324940152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4679017066955566, "target_z": 2.093749840744538, "ce": 6.173524379730225, "genuineness": 3.6287014484405518, "identity": 0.291504442691803, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/af28426495157d0b07221275f2596e2821c791ead29f329cd97b22ecfdbfb66b.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "af60981806a2de923ff3887a61085b48d98a547e87e9454fc30e0464120c742f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "eaacfa50418c4d97a7b82d867d31a7f6094b1fb94f4d305898b97821561e3228", "generation_seconds_batch": 23.442832235014066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22584590315818787, "target_z": -0.21484376125174462, "ce": 6.316492557525635, "genuineness": 4.306513786315918, "identity": 0.8158236145973206, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/af60981806a2de923ff3887a61085b48d98a547e87e9454fc30e0464120c742f.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "af862da16a50416036e5ab1fb86e1e431c9e7ce04515d86e159c518241f1612f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "92add49756ac3be11e63aef59adf4f71faf200cfb0e7af5132d0e40307a9d657", "generation_seconds_batch": 22.660532535985112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.795754075050354, "target_z": 2.7031249411447207, "ce": 6.221180438995361, "genuineness": 3.785602569580078, "identity": 0.5156067609786987, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/af862da16a50416036e5ab1fb86e1e431c9e7ce04515d86e159c518241f1612f.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "afc8b108a264f48fa9c80d07bc6997be5e261d994c390c6bddfa9e541e75db22", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "eb1de64cba063f937e4d82f35f861ed9c9eaf7d68339e0fc484bb1b27564878e", "generation_seconds_batch": 25.676181102986448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.636031150817871, "target_z": 2.406249937682645, "ce": 6.324435234069824, "genuineness": 4.168440818786621, "identity": 0.24599182605743408, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/afc8b108a264f48fa9c80d07bc6997be5e261d994c390c6bddfa9e541e75db22.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "b03dddb81926c3763f623f144ab7415ca294af799c60a6039f3cac67bb35f8c9", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fc078ddc548818246421d7eff4b89e48f087cfd96883a58deded91f23fe037c5", "generation_seconds_batch": 17.65182835503947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5271170139312744, "target_z": 4.062500096938107, "ce": 6.3641486167907715, "genuineness": 4.105680465698242, "identity": 0.5893536806106567, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/b03dddb81926c3763f623f144ab7415ca294af799c60a6039f3cac67bb35f8c9.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "b07b1f3de8e622e3d394c549d6c68ea759bc4a64ada478cb0c9bf8815a546d8d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1b32e201a9c8f2a7d8977e17eee8c59b9f39727991884a551f89cbb907d63be1", "generation_seconds_batch": 24.13441788207274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0475783348083496, "target_z": 1.312500041544903, "ce": 6.284721851348877, "genuineness": 4.344170093536377, "identity": 0.669877827167511, "hypothesis": "J'ai trouvé la 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_Teasing/b07b1f3de8e622e3d394c549d6c68ea759bc4a64ada478cb0c9bf8815a546d8d.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "b12603127843218747c4d406f7836bc378581d655569ed0760b1406396dd4d1f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "dc527e604d984368bbb66f59959277b1fc9676c0d9d3863231b8336f0caa15b6", "generation_seconds_batch": 16.18058248597663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.228317379951477, "target_z": 1.6484374463378335, "ce": 5.998785495758057, "genuineness": 4.005263805389404, "identity": 0.48946183919906616, "hypothesis": "La puerta sigue abierta y he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/b12603127843218747c4d406f7836bc378581d655569ed0760b1406396dd4d1f.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "b15aa75b6a4c8398545c09ba161e0b461f0b3c5dfd84f08ff38d6213aaf79811", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "4f66dd70feab9bcfb94a903ba19c6f5aa4ee3d974ab9cd2da0d6b8867a949707", "generation_seconds_batch": 23.814453003928065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1820818185806274, "target_z": 1.562499986151699, "ce": 6.372091293334961, "genuineness": 3.9173994064331055, "identity": 0.39159393310546875, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/b15aa75b6a4c8398545c09ba161e0b461f0b3c5dfd84f08ff38d6213aaf79811.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "b37b1877171cdb720e041b99ada6f4a4785aee08a2d197318a7ddd2277eecdfd", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c505051c82d4132534903ee0409fb231ccd6d80e3862f1d2378525fef2f83e77", "generation_seconds_batch": 24.301285030087456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7369087934494019, "target_z": 2.5937499515309463, "ce": 6.133810997009277, "genuineness": 3.9425034523010254, "identity": 0.3526475131511688, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/b37b1877171cdb720e041b99ada6f4a4785aee08a2d197318a7ddd2277eecdfd.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "b3fe88692609bd47cd5311b390f96a19b66e9bb5d8dbd7e71fad0fa565263c70", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3f57023d728f9bbe89a3f50a02330f1c05e35b3500ea479ac9c35a13d2aa5897", "generation_seconds_batch": 25.11878526106011, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2115044593811035, "target_z": 1.617187480958586, "ce": 6.0305562019348145, "genuineness": 4.017816066741943, "identity": 0.6338251233100891, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/b3fe88692609bd47cd5311b390f96a19b66e9bb5d8dbd7e71fad0fa565263c70.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "b40a85df7688e1282947857c1186fe20b6c58a4b82968d0c8a678c720ded3afe", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3451c7c193788acddd40d7203c0ab9be21d9aa0395dbdc9288f20ee36ba63973", "generation_seconds_batch": 17.459966548951343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.384207010269165, "target_z": 3.7968750588552793, "ce": 6.046441555023193, "genuineness": 4.425758361816406, "identity": 0.6911152601242065, "hypothesis": "I've tried the petite boat. It is pretty lay fenêtre. We've regarded ensemble.", "wer": 0.8421052631578947, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/b40a85df7688e1282947857c1186fe20b6c58a4b82968d0c8a678c720ded3afe.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "b40e9749b8de6f369c2f0fe8955712880cc3c7bf59fbc9ada2c2b39a821994f2", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3776164402e22371c5ac9d552a63fab393984a8ea2a03679a16bd217693a02ec", "generation_seconds_batch": 22.16124658600893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0265620946884155, "target_z": 1.2734374186412314, "ce": 6.268836498260498, "genuineness": 4.287685871124268, "identity": 0.5955129265785217, "hypothesis": "J'ai trouvé la 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_Teasing/b40e9749b8de6f369c2f0fe8955712880cc3c7bf59fbc9ada2c2b39a821994f2.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "cd693896b07426d8601fafd41704c7b9cd41917ca682f41838650381426c3516", "generation_seconds_batch": 18.560719821951352, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25316694378852844, "target_z": -0.16406248442066132, "ce": 6.372091293334961, "genuineness": 4.055472373962402, "identity": 0.6338757276535034, "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_Teasing/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "b4d85b58c08d68871dab2ed6e4db3e6c8953531eda60dc0ac99c7a80c7b85617", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "99488e6a8e6ccddec916b54806b311d7e24502fc01c030881bb5cc7e8ed08014", "generation_seconds_batch": 25.098366640973836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39344990253448486, "target_z": 0.0966796981026055, "ce": 6.356205940246582, "genuineness": 4.049196243286133, "identity": 0.4145612418651581, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/b4d85b58c08d68871dab2ed6e4db3e6c8953531eda60dc0ac99c7a80c7b85617.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "b51722d8430a3f2bcdbe50a8b3323d29fb2b4a3a1e99dc510cbf9133dc1f43d1", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2cf01e0e833496e30fe6303b624a05480c627e5262f2293be63bc4699b24a646", "generation_seconds_batch": 17.233040251070634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8714122772216797, "target_z": 2.843749896137742, "ce": 6.340320587158203, "genuineness": 4.231201171875, "identity": 0.6256745457649231, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/b51722d8430a3f2bcdbe50a8b3323d29fb2b4a3a1e99dc510cbf9133dc1f43d1.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "b560d1dc065b4ba9211456f7f41603bb731cb131ab5ab59b2d7eb80bfe52c46a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1b9494bb03cf3d57c4d7ef1cfd02dfa81e1714dc8b5a5840312e36bef37ea794", "generation_seconds_batch": 23.06217030901462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.417462944984436, "target_z": 1.9999999446067958, "ce": 6.125868320465088, "genuineness": 4.256305694580078, "identity": 0.5763893127441406, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/b560d1dc065b4ba9211456f7f41603bb731cb131ab5ab59b2d7eb80bfe52c46a.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "b62ff6b616642207130304c0322e904beba5c6b293ec95ee7cc0494cd2eeca96", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b1355aa9b795adcfe34f3a02fa27e1a6a8f900ba26893cb037ab673938ae9e71", "generation_seconds_batch": 25.062465770053677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.031135320663452, "target_z": 3.140625121172634, "ce": 6.125868320465088, "genuineness": 4.18726921081543, "identity": 0.6071720123291016, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/b62ff6b616642207130304c0322e904beba5c6b293ec95ee7cc0494cd2eeca96.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "b693564b5122753b9f54139cc1e3dd89ce5bd5c295746811fd928938535a4a96", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "90201d58b953f042d0a096f1539a0a8cd905b2ce00eb809ebcbdd824561e81b9", "generation_seconds_batch": 23.666363507974893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6444376707077026, "target_z": 2.4218750311586774, "ce": 6.125868320465088, "genuineness": 3.973883628845215, "identity": 0.2876606583595276, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/b693564b5122753b9f54139cc1e3dd89ce5bd5c295746811fd928938535a4a96.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "b7928d326e559b9412664d3d3653e7bed8b664d7b40fd264228b5486948c560e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6c12ce3db91fd54c47b2a2130fb2e705637356cf660b51bf66e56b0f63151454", "generation_seconds_batch": 22.897311302949674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7032829523086548, "target_z": 2.5312500207724518, "ce": 5.95112943649292, "genuineness": 3.9299514293670654, "identity": 0.42936190962791443, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/b7928d326e559b9412664d3d3653e7bed8b664d7b40fd264228b5486948c560e.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "b8254c0b41fb11c002a25877c393b675b678121ac45ba93d9841d98b8266e199", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0ac4869e83944a20c5ee2e56dcf07ebde515f4d4daa7cadcfc09aacb02528b41", "generation_seconds_batch": 17.528949655010365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.161065697669983, "target_z": 1.523437584820844, "ce": 6.268836498260498, "genuineness": 4.381826400756836, "identity": 0.7136645317077637, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/b8254c0b41fb11c002a25877c393b675b678121ac45ba93d9841d98b8266e199.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "b83e6c3e96e21f975ddae6016db49fb9b47892f6b6779b3e5554dc4fd88f9bdb", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "cb8bc4d6aa3073241637f051151c2c5d48b0c18f13ae05eed1d170c8351dcaa7", "generation_seconds_batch": 24.34862036490813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9218511581420898, "target_z": 2.937500013848301, "ce": 5.990842819213867, "genuineness": 3.5314228534698486, "identity": 0.5306791067123413, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/b83e6c3e96e21f975ddae6016db49fb9b47892f6b6779b3e5554dc4fd88f9bdb.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "b852ae321d8a8ce9cb19d223d577190392c7187ee70c582b4bdb4bc4869764b8", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3aed933b2a891e840fbfc8f5f0aeed5059980aa3922c95b8b57c00fcc8980394", "generation_seconds_batch": 19.796068584080786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.034968614578247, "target_z": 1.2890625121172634, "ce": 6.205295085906982, "genuineness": 3.6475296020507812, "identity": 0.5172149538993835, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/b852ae321d8a8ce9cb19d223d577190392c7187ee70c582b4bdb4bc4869764b8.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": "b948bbb7d6e3e0b0cdacc695c688c8a1f47a8bcaa12146915693be335b023272", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "15a8d32efaad7e9469585ef8941265c406ed5b49625291a808db6338fd190133", "generation_seconds_batch": 19.887559960014187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.224114179611206, "target_z": 1.6406250103862259, "ce": 6.157639026641846, "genuineness": 4.293961524963379, "identity": 0.6276764869689941, "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_Teasing/b948bbb7d6e3e0b0cdacc695c688c8a1f47a8bcaa12146915693be335b023272.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "b9a3ca32a8f4a825a11288990fd1f87d0af71ee0f03b1f1cd48d7bcc14c260cc", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "480a22ecf7a441f48367c6e49ab02f08b237eea27614e613d17df74c47e7274e", "generation_seconds_batch": 24.529667459079064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4850847721099854, "target_z": 3.9843752942763975, "ce": 6.213237762451172, "genuineness": 3.7793264389038086, "identity": 0.3612177073955536, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/b9a3ca32a8f4a825a11288990fd1f87d0af71ee0f03b1f1cd48d7bcc14c260cc.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "b9bbea3553c9fc707dfcf819a47f1e00376bc2d41fb56a3292261f2952f82522", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d3c687a731d88737e045a9e6979c1c4b76f6411c4bd613c7d46fcf792f7414bb", "generation_seconds_batch": 16.66378880001139, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0980170965194702, "target_z": 1.4062499376826452, "ce": 6.09409761428833, "genuineness": 4.256305694580078, "identity": 0.644438624382019, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/b9bbea3553c9fc707dfcf819a47f1e00376bc2d41fb56a3292261f2952f82522.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "ba10e3571477096569e02090d55083cf7789c8822d1d04130aa07d5a8e20efad", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4b50fc786392f6c70b51c6b990df2326cfac09ec0886a6f53afb6feb4540a606", "generation_seconds_batch": 16.39244113897439, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13022232055664062, "target_z": -0.3925781193741277, "ce": 6.229123115539551, "genuineness": 4.068024158477783, "identity": 0.6155555248260498, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ba10e3571477096569e02090d55083cf7789c8822d1d04130aa07d5a8e20efad.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "ba17c9a68d7dcf5d91d458ec0947c9295937ea8e80b51249e38376a8fe24d401", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8b3bcc19a7589ec9b1e3a1c6d4010b0e75b73b378250ecb2049bbcb04d7bbd68", "generation_seconds_batch": 22.26513466099277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8461928367614746, "target_z": 2.7968748372824628, "ce": 5.7247633934021, "genuineness": 3.7542223930358887, "identity": 0.22443726658821106, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können.", "wer": 0.125, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ba17c9a68d7dcf5d91d458ec0947c9295937ea8e80b51249e38376a8fe24d401.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "e9b205cd2c80191b347792f2fdd535042746eaa7b0bdbcf792f8df995b3b37fe", "generation_seconds_batch": 17.07977716298774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06191974878311157, "target_z": -0.5195312560586317, "ce": 6.149696350097656, "genuineness": 4.557555198669434, "identity": 0.7374378442764282, "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_Teasing/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.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": "ba8195f167c7f21e84d08e6ebe8a948b465fd2d0064e835725b605642355602d", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0b6a5d1b59d01f74323f94562098d722abd1ad4627548f8989d3fb1617107c9a", "generation_seconds_batch": 25.649903555982746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5855923891067505, "target_z": 2.312500041544903, "ce": 6.403861999511719, "genuineness": 4.15588903427124, "identity": 0.5578545331954956, "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_Teasing/ba8195f167c7f21e84d08e6ebe8a948b465fd2d0064e835725b605642355602d.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": "babf1161eb67566733f7afa255e4d6a60983198f3a5dd9720dc29a668032756c", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0b71d3b8c952dad8120ae0b16ccb5c72efa26c004468ce308c832ece59e9f9e6", "generation_seconds_batch": 17.44144995592069, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2871626615524292, "target_z": 1.7578124359516076, "ce": 6.181467056274414, "genuineness": 4.124508857727051, "identity": 0.6110256910324097, "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_Teasing/babf1161eb67566733f7afa255e4d6a60983198f3a5dd9720dc29a668032756c.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "bad70372cae832994b85fd71dd18fb6de67926310467dcf7c1b0827d7155fd5e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "9cdd6db71d7d8ad28feb2e4f6681c85251d3052cded7a39054d9a78a17d638a8", "generation_seconds_batch": 24.803426358033903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5855923891067505, "target_z": 2.312500041544903, "ce": 6.038498878479004, "genuineness": 3.9927117824554443, "identity": 0.580595076084137, "hypothesis": "Ik 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_Teasing/bad70372cae832994b85fd71dd18fb6de67926310467dcf7c1b0827d7155fd5e.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "bb4f571222c1d93f12fca86b6fb791c12d36559843fe898c59c9f322ac19e9f5", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8ca184f79f5e8c503d9b07a7d534dcac17c42bcbb1c465c9ec65ae026c218294", "generation_seconds_batch": 20.34164239000529, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5855923891067505, "target_z": 2.312500041544903, "ce": 6.284721851348877, "genuineness": 4.331617832183838, "identity": 0.3266940116882324, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/bb4f571222c1d93f12fca86b6fb791c12d36559843fe898c59c9f322ac19e9f5.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "bbebb8573b91610c47d3654a5503b4f5d298c480e55c1552bd997422ea3497ac", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e0f6673dba85ec5da6fa3320d021a3c99eebbefb857ad1c94756f152e93eb854", "generation_seconds_batch": 22.314878992037848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7116893529891968, "target_z": 2.546874892675667, "ce": 6.109982967376709, "genuineness": 4.18099308013916, "identity": 0.5648999810218811, "hypothesis": "Hmm, I've tried the petite boite. Elle is pretty de la vie fenêtre. We regard ensemble what.", "wer": 0.7368421052631579, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/bbebb8573b91610c47d3654a5503b4f5d298c480e55c1552bd997422ea3497ac.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "bbf7cbcbf24334fbdb3e47c33dc5d0796f29e0d3b824777dc955f8f6806e5f3f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ce4a3d2205d84693320d6eb11d7108a927a14b8221bc8e559f1444ed8e166106", "generation_seconds_batch": 25.12477785698138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.770534634590149, "target_z": 2.656249882289441, "ce": 6.221180438995361, "genuineness": 3.562803030014038, "identity": 0.2882152795791626, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/bbf7cbcbf24334fbdb3e47c33dc5d0796f29e0d3b824777dc955f8f6806e5f3f.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "bc70f621c68a292a87748237d6c167bcca8da217e0517a8ec4b0f4920bf9c4e9", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d494fe357930d9d84929b536704a0d0e3bc41e9127a4e0d790cc1b998ae620ef", "generation_seconds_batch": 22.314878992037848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2913659811019897, "target_z": 1.765625093476032, "ce": 6.006728172302246, "genuineness": 4.042920112609863, "identity": 0.5828741192817688, "hypothesis": "Je trouve la petite boite. Elle était prêt de la vie fenêtre. We want regard ensemble.", "wer": 0.5789473684210527, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/bc70f621c68a292a87748237d6c167bcca8da217e0517a8ec4b0f4920bf9c4e9.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": "bcce1c01e7502269def9cdbc059166e0f2cfb255a09add6a5d8df1b8db1bf4c8", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9fa4d84f5a36fb8291578c1495e0cce9bd7381c4c6a2420eb11cee118895ffff", "generation_seconds_batch": 18.85566410503816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2497034072875977, "target_z": 3.546874892675667, "ce": 6.3641486167907715, "genuineness": 4.325342178344727, "identity": 0.5989526510238647, "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_Teasing/bcce1c01e7502269def9cdbc059166e0f2cfb255a09add6a5d8df1b8db1bf4c8.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "bd4555e671cd17ce1f073d11134820f9b4d0bdf8827283b6d0f550a1cd817247", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0482b80f49ebb68e165f4f70a433b1ad091ef92fbaeec29838c041736427f28b", "generation_seconds_batch": 25.851031793048605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.728872299194336, "target_z": 4.43750012463471, "ce": 6.006728172302246, "genuineness": 4.174716949462891, "identity": 0.2386581003665924, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/bd4555e671cd17ce1f073d11134820f9b4d0bdf8827283b6d0f550a1cd817247.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "bd9a09be681e48f82ad5fc82fa5ae90505b009f173d910a32895f8a409119593", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8fac954ce3e6d9c4627a2d59b16495a329f1e136b89d113f6b58d90b0d8df9f2", "generation_seconds_batch": 18.831280810991302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.695246458053589, "target_z": 4.375000193876215, "ce": 6.086154937744141, "genuineness": 4.300237655639648, "identity": 0.37227538228034973, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/bd9a09be681e48f82ad5fc82fa5ae90505b009f173d910a32895f8a409119593.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "bdad04d5a3dffc280caebaca9c0ab4d532d3063e5ff35155e12903d184d100a3", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6a63fcf95c8c5fbabb7175e2d9d3430afef53df04196e69d84326006aac03467", "generation_seconds_batch": 23.768547072075307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3418047428131104, "target_z": 1.8593749896137741, "ce": 6.260893821716309, "genuineness": 4.168440818786621, "identity": 0.6168636083602905, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/bdad04d5a3dffc280caebaca9c0ab4d532d3063e5ff35155e12903d184d100a3.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "bdf00c05f1d26ab5c39e187594437d146c69fe49da030ef82ece9dbc5dfd5862", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "36d913f23cf050289d2223a12a90be5c8cddd0bfb27cf675b32159938838d0c0", "generation_seconds_batch": 21.921728587010875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4874972701072693, "target_z": 0.2714843650465336, "ce": 6.356205940246582, "genuineness": 4.281409740447998, "identity": 0.6989585161209106, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/bdf00c05f1d26ab5c39e187594437d146c69fe49da030ef82ece9dbc5dfd5862.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "bdf7c3a65fad5f9cd8894cc6049f031ad5405e061e6bfc442eb2f52746f902b7", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "878dc28e2db194ed4d8d3e16fd14d96fed77d059b21897d77d4af94e1f30f9d6", "generation_seconds_batch": 17.329807152971625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9470704793930054, "target_z": 2.9843748511307635, "ce": 6.1894097328186035, "genuineness": 3.7667744159698486, "identity": 0.2336960732936859, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/bdf7c3a65fad5f9cd8894cc6049f031ad5405e061e6bfc442eb2f52746f902b7.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "bf2fb0e849133c8be8cc635a2a7661f326363716a5fb7ce9046cffa4614d1116", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b8649f9ba3ad29a5f92582601f94b1e78a530cb3ba45747a61645240adfa7072", "generation_seconds_batch": 25.041427804972045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8521279096603394, "target_z": 0.9492187785621209, "ce": 6.229123115539551, "genuineness": 3.8797430992126465, "identity": 0.47567006945610046, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/bf2fb0e849133c8be8cc635a2a7661f326363716a5fb7ce9046cffa4614d1116.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "bf34bf93ea66f06f37dcd6e07cb97401de1502b444b178da97be12ed90624857", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "80ad91b44fe3dde8d0fb2927a9db8b0c3c44c4dd23fcacd53155ad3accebd283", "generation_seconds_batch": 23.442832235014066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.169472098350525, "target_z": 1.5390624567240592, "ce": 6.292664527893066, "genuineness": 4.193545341491699, "identity": 0.5907108783721924, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/bf34bf93ea66f06f37dcd6e07cb97401de1502b444b178da97be12ed90624857.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "bf577e48f5edb7026442a7eb27e7c7a4d55337b44814adce4dc47a5372d8bcbc", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6d0e360bffabdc4a087fa1f0f00a77f3abfba6064117a36014725ac94a14fa66", "generation_seconds_batch": 26.928479771944694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39975476264953613, "target_z": 0.10839846281642537, "ce": 6.173524379730225, "genuineness": 3.9801597595214844, "identity": 0.6102111339569092, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/bf577e48f5edb7026442a7eb27e7c7a4d55337b44814adce4dc47a5372d8bcbc.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "bf63c71fac083c562d5d335694b87ae42a2915bd8f1b58ff7799bf5d87432dda", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f9944555a294687a73419625dd17f3975f95c8ef74a64ef70baf6b30e1073af4", "generation_seconds_batch": 24.876538424985483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8332133293151855, "target_z": 0.9140624844206613, "ce": 6.0305562019348145, "genuineness": 4.293961524963379, "identity": 0.6505218744277954, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/bf63c71fac083c562d5d335694b87ae42a2915bd8f1b58ff7799bf5d87432dda.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "bf66715780b5b04eb23dadb69782d5494e8997a107425291855e6f69baa57f3c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6962f114ecebd248ee2f333806f4158cdde2e02673adbe93f6905226db935399", "generation_seconds_batch": 26.338911270024255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4006500244140625, "target_z": 1.9687499792275485, "ce": 6.292664527893066, "genuineness": 4.055472373962402, "identity": 0.7293273210525513, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We've regarded ensemble what it contains.", "wer": 0.3157894736842105, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/bf66715780b5b04eb23dadb69782d5494e8997a107425291855e6f69baa57f3c.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "bfd92bec59d8e4d0a9870ac8b51b06d53b63b4e038c024813093ba60162ff77e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "84ccb6fa396872b05ceadcbd184abd9a29c6763151010433b470539b7406ddc1", "generation_seconds_batch": 25.772655499982648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.762128233909607, "target_z": 2.6406250103862257, "ce": 6.181467056274414, "genuineness": 3.8797430992126465, "identity": 0.4578600525856018, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/bfd92bec59d8e4d0a9870ac8b51b06d53b63b4e038c024813093ba60162ff77e.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "bfee957fe11674b13d41efa823f2f3fb36d2ade6e262d8b1ab87207173e73e39", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0480898f2d6db2601dcbc6d5cb1ab58659c86a42456e008a8ae713504a8acaab", "generation_seconds_batch": 23.070804376038723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3586176633834839, "target_z": 1.8906249549930216, "ce": 6.4912309646606445, "genuineness": 3.9676074981689453, "identity": 0.6073037981987, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/bfee957fe11674b13d41efa823f2f3fb36d2ade6e262d8b1ab87207173e73e39.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "c06a522cd16cee8f7063942ac9890e18abecb03ca53ec75a1b2f0dbcfb32b731", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "43768596385a8a79baeaa4ef692b02fe4075c4bc4080555bf458c6deb4aa41fe", "generation_seconds_batch": 24.907558926963247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.443052291870117, "target_z": 3.9062500484690537, "ce": 6.09409761428833, "genuineness": 3.4090399742126465, "identity": 0.28812915086746216, "hypothesis": "The 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_Teasing/c06a522cd16cee8f7063942ac9890e18abecb03ca53ec75a1b2f0dbcfb32b731.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "c06a53edefe0dc6be9838ac70e5d0a00cb91f9afec12c00b49425c3acf158a67", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "827b78db9ffeaeaf666edd76302fe948108f8fa2bcd33753a09e3a4149813011", "generation_seconds_batch": 16.826161695062183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.081943988800049, "target_z": 5.093750062317355, "ce": 6.165581703186035, "genuineness": 4.1998209953308105, "identity": 0.3832382559776306, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c06a53edefe0dc6be9838ac70e5d0a00cb91f9afec12c00b49425c3acf158a67.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "c0787ff435d8faeec7977fe9b561e0c24cf52c2274b20a052887c546355615e7", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b0f3cbcaa45e15ea0f14ef83d8709680a19834db50726807c6afec7d43829e45", "generation_seconds_batch": 25.814632244990207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7008114457130432, "target_z": 0.6679687577896694, "ce": 6.4912309646606445, "genuineness": 4.306513786315918, "identity": 0.6143712997436523, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c0787ff435d8faeec7977fe9b561e0c24cf52c2274b20a052887c546355615e7.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": "c07f61657d22c138a84f440033876a9cd3b30c1731936b186e440c29b4175e52", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "49e82b4e2d39f97a39844abf2323b03c02e52eb84018583f2dc55c3eb3c22be8", "generation_seconds_batch": 17.93444585602265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3964468240737915, "target_z": 1.9609375432759408, "ce": 6.340320587158203, "genuineness": 4.281409740447998, "identity": 0.41237854957580566, "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_Teasing/c07f61657d22c138a84f440033876a9cd3b30c1731936b186e440c29b4175e52.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "c08ebedfe9c305712c12ed4415686e4daa548ea940f66ce52264bbd58d736ac9", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e015ad1ba13cdd46f21ca09156baa3ecf137ca74785bd8b2056ccdc97f100727", "generation_seconds_batch": 26.663519599009305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39686501026153564, "target_z": 0.10302731616158774, "ce": 6.165581703186035, "genuineness": 4.293961524963379, "identity": 0.7460006475448608, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c08ebedfe9c305712c12ed4415686e4daa548ea940f66ce52264bbd58d736ac9.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "c0af6811015abc70db88c05a57edd559ccb9044fbce4ed5e71df92c4c23828af", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "eeee72b503ad694428d9a667c4ef283412cf0a21ed32c95ecb930b127c796fe9", "generation_seconds_batch": 22.497601618990302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2157076597213745, "target_z": 1.6249999169101936, "ce": 6.0146708488464355, "genuineness": 4.425758361816406, "identity": 0.6149860620498657, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c0af6811015abc70db88c05a57edd559ccb9044fbce4ed5e71df92c4c23828af.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "c0e345abfb5007c28e6c34385fda47699caa0b9180f43200a9474baf2644e02b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1a9c96db8ab9db7e6cc6f1a456a9340e3f529b3f82a80808a6964d7f72ee2e9a", "generation_seconds_batch": 23.202503715991043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.762498140335083, "target_z": 4.500000055393204, "ce": 6.181467056274414, "genuineness": 3.923675537109375, "identity": 0.2856699824333191, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c0e345abfb5007c28e6c34385fda47699caa0b9180f43200a9474baf2644e02b.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "c1072d1ca344337b788997d3e101240a01bab2a3983900a57b79fa65c5f0b99c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "59f51faeb409895f5ace59ca2fc8e22bb40019ceddb5bb2ebad4a060eb290006", "generation_seconds_batch": 21.633840478025377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8377864360809326, "target_z": 2.7812499653792475, "ce": 6.268836498260498, "genuineness": 4.381826400756836, "identity": 0.5371536016464233, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c1072d1ca344337b788997d3e101240a01bab2a3983900a57b79fa65c5f0b99c.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "c13df828d40e0e042bdbd83180e542921afa86bed6726f19e3a58ba693760f13", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e65307db9025767aefbd81e780767fc8e8b4f4c2e235e22ae257f833287946d9", "generation_seconds_batch": 24.765801645000465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1320128440856934, "target_z": 3.3281249134481183, "ce": 6.086154937744141, "genuineness": 4.049196243286133, "identity": 0.7129279971122742, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c13df828d40e0e042bdbd83180e542921afa86bed6726f19e3a58ba693760f13.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "c188cedcab7b8eb956e0e6d2c91a862c877ffbaadc08b78a45a99ee66db937c6", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "697c1796c45645671ec02b01268a3b057ea8e1b447f26695c04d278bd829a04f", "generation_seconds_batch": 22.763406035024673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.383837103843689, "target_z": 1.937500013848301, "ce": 6.300607204437256, "genuineness": 3.8420867919921875, "identity": 0.6783111691474915, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c188cedcab7b8eb956e0e6d2c91a862c877ffbaadc08b78a45a99ee66db937c6.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "c1cc46052825622c2e928a396b92e4793ed729aa7d54b681b48561e14879d95b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b450e7baefc12919f14d6c758cb7e33347810d3ace2089133b780e753d409ce1", "generation_seconds_batch": 17.584697530954145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3929244875907898, "target_z": 0.09570311591205242, "ce": 6.078212261199951, "genuineness": 3.998987913131714, "identity": 0.5759667158126831, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c1cc46052825622c2e928a396b92e4793ed729aa7d54b681b48561e14879d95b.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "c1efc736c5f032b26237bf8677a7a52d6176041608a3f7a786940a7e4da02d96", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "27208d0706793f0e74b41faae56e77928713a891e78a98b05433397e43eb7f3f", "generation_seconds_batch": 25.676181102986448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8458230495452881, "target_z": 0.9375000138483011, "ce": 6.3641486167907715, "genuineness": 4.287685871124268, "identity": 0.5582930445671082, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c1efc736c5f032b26237bf8677a7a52d6176041608a3f7a786940a7e4da02d96.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "c1fa66b15c23c2a2f250d9e01c23fc456029d1d31d79f30c2c1058a42b8bfd32", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "796809ca85a4f396ac2ade8c88d22075df6a697e3f7527342167f37d27959fdb", "generation_seconds_batch": 18.2316890549846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.300142288208008, "target_z": 3.6406250103862257, "ce": 5.990842819213867, "genuineness": 3.8922953605651855, "identity": 0.5684851408004761, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c1fa66b15c23c2a2f250d9e01c23fc456029d1d31d79f30c2c1058a42b8bfd32.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "c22a40289189b51de3f4752a9fafe779c557ae45f8e5570bfe83b6a3cfd9d647", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cca93b72e1d85214d9427e729b0be52870b0f38a81979eaf5222d4db46044954", "generation_seconds_batch": 19.701561143039726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9638835191726685, "target_z": 3.015625038082828, "ce": 6.125868320465088, "genuineness": 3.9927117824554443, "identity": 0.6429517269134521, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c22a40289189b51de3f4752a9fafe779c557ae45f8e5570bfe83b6a3cfd9d647.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "c23d719bd390847f81ee5eef23aad5debd900417737adc9b35e9386180c2c4c1", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "791cc976bf2474f3261ae8991d7490e66ebadaa65adecd773ba20c8a65f5ceb4", "generation_seconds_batch": 25.730458584963344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0433751344680786, "target_z": 1.3046876055932957, "ce": 6.229123115539551, "genuineness": 3.8922953605651855, "identity": 0.3469782769680023, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c23d719bd390847f81ee5eef23aad5debd900417737adc9b35e9386180c2c4c1.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "c3776ba737840c97fe8ce01a9f8b2fe686f77cd634bc6afdafc1afdc7ad1d7a1", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "79ebfe64ed074ef9dd29efcb580e0ccb353a2243bb62811053bcb6554de009af", "generation_seconds_batch": 16.810128369019367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5351535081863403, "target_z": 2.218749923834344, "ce": 6.38003396987915, "genuineness": 4.193545341491699, "identity": 0.5845712423324585, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c3776ba737840c97fe8ce01a9f8b2fe686f77cd634bc6afdafc1afdc7ad1d7a1.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "c38b487a026c8518e6d111753783342e56035dae9e6553d6aaf6afaaaecba8ae", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cd550ae16329d74c198cf5e43383d3a9a4a482a20381f3fc0cee36e47178fb5e", "generation_seconds_batch": 21.315445304033346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1316430568695068, "target_z": 1.468750090013957, "ce": 6.284721851348877, "genuineness": 4.105680465698242, "identity": 0.6591317653656006, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c38b487a026c8518e6d111753783342e56035dae9e6553d6aaf6afaaaecba8ae.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "9d02da022fcbd939fe5ab548742d2849d20074bd9b40b2c9eebf8113a4d67bb1", "generation_seconds_batch": 19.183410948957317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08713915944099426, "target_z": -0.47265625259655647, "ce": 6.046441555023193, "genuineness": 4.21237325668335, "identity": 0.48132550716400146, "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_Teasing/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "c3ce9da2550169a4252e85200b4c5cb3cd76a6807246a802933bf045afb2664d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "03cc8252c295412f5eb99e13cdfad2658f084a2e971970f109871f30bd824208", "generation_seconds_batch": 23.00366273301188, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4679017066955566, "target_z": 2.093749840744538, "ce": 6.229123115539551, "genuineness": 4.017816066741943, "identity": 0.4871627688407898, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c3ce9da2550169a4252e85200b4c5cb3cd76a6807246a802933bf045afb2664d.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "c3ff406519c694111be92bb8bc9d3b954dff97c84fdc9fed357ced2bdbcd3853", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d0a5ed5d867cf71c667548ad02ed11a14b1cb2228d9d478b06037d72667cf1d3", "generation_seconds_batch": 16.703919474966824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5183405876159668, "target_z": 2.187499958455097, "ce": 6.149696350097656, "genuineness": 3.835810661315918, "identity": 0.5904030799865723, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c3ff406519c694111be92bb8bc9d3b954dff97c84fdc9fed357ced2bdbcd3853.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "c418abb44532a1a1c3f37ff5c7ffe8f7e8a39f1b13aef4a2e7e98d52047e5aa2", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "190c315852b51a1c0cb21029ad089cac8586d21af18fb66b49f572203130114f", "generation_seconds_batch": 24.849846267024986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.820973515510559, "target_z": 2.75, "ce": 5.990842819213867, "genuineness": 4.3127899169921875, "identity": 0.4859233498573303, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c418abb44532a1a1c3f37ff5c7ffe8f7e8a39f1b13aef4a2e7e98d52047e5aa2.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "c435120fa64e63bb409a9cd0f0f255962c040cb4f775905e85e2f7ba988be5d6", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a72bdb49f32e3f7358c3494ff7f174502c9ba8fa5d6a9f5fbecb47a606a300d3", "generation_seconds_batch": 25.062465770053677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6776936054229736, "target_z": 0.6249999169101936, "ce": 6.213237762451172, "genuineness": 4.507347106933594, "identity": 0.6641572713851929, "hypothesis": "De deur staan nog open. Ik heb je jas op de stoel gelegd. Zeg, maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c435120fa64e63bb409a9cd0f0f255962c040cb4f775905e85e2f7ba988be5d6.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "2be31e60cdfee674ff07e44698ae63bab047d8922a2420b774acdc248ce02895", "generation_seconds_batch": 18.245699661085382, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20062650740146637, "target_z": -0.26171873701721776, "ce": 6.316492557525635, "genuineness": 4.570107460021973, "identity": 0.6505722999572754, "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_Teasing/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "c494d99bea5cd678ae9620b5123bd2a115bb97489eb8fc3dc8d60ee2c628a542", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "39598f708d5996360358abb618bf5b833f8b127f683d918b2182584c8d148ed9", "generation_seconds_batch": 24.471357174101286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.35898756980896, "target_z": 3.75, "ce": 5.903473377227783, "genuineness": 3.8420867919921875, "identity": 0.5678685903549194, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c494d99bea5cd678ae9620b5123bd2a115bb97489eb8fc3dc8d60ee2c628a542.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "c4ae4e975da224e8fa8ec6c0c293762c3a985f2655d4ca4de21231a25a8e38ac", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "39868c033b8c08645970946fec94f40642c78ef049494f03dd466d07790e1315", "generation_seconds_batch": 25.12477785698138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8714122772216797, "target_z": 2.843749896137742, "ce": 6.284721851348877, "genuineness": 3.653805732727051, "identity": 0.26915204524993896, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c4ae4e975da224e8fa8ec6c0c293762c3a985f2655d4ca4de21231a25a8e38ac.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": "c4c0b94943d753959c23efe77b6883df3bf2e7e97b2eece791a9de8bdaec7a98", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "560113acbcfad2ad1a90b8d5c26d505f1314fa0e0a41560590cb0d3eb2b43960", "generation_seconds_batch": 17.487501519033685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1404194831848145, "target_z": 3.3437502284969676, "ce": 6.268836498260498, "genuineness": 3.9048471450805664, "identity": 0.40897947549819946, "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_Teasing/c4c0b94943d753959c23efe77b6883df3bf2e7e97b2eece791a9de8bdaec7a98.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "c52d844eba401964b95bd666f703785edd2c2be96c7e815a99eac2a2c16a6221", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b2c2ee7f83eb5f1a7754e5c6b62876cd4f304fdc367c26e75248ced3c501c17f", "generation_seconds_batch": 33.34550406807102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8437213897705078, "target_z": 0.9335936850860888, "ce": 6.141753673553467, "genuineness": 4.18726921081543, "identity": 0.5724034309387207, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c52d844eba401964b95bd666f703785edd2c2be96c7e815a99eac2a2c16a6221.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "c55fd1c2e92202e32f756719da269c5a4914e5cb369b1d5c27b1259009b372a0", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b10ec7a27cbddd86218f13134e14ac1f1711c8ad25cced32ff397b0727073775", "generation_seconds_batch": 24.202861278085038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9593104124069214, "target_z": 1.1484375571242418, "ce": 6.229123115539551, "genuineness": 4.049196243286133, "identity": 0.3935130834579468, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c55fd1c2e92202e32f756719da269c5a4914e5cb369b1d5c27b1259009b372a0.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "c57bd96ae191b3fb271820caa7fd689e0986d960f62f368c1f332eb4b31df571", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "bac4fda02ccfbf4bc0e03cfbe86361e05d337f3c1f5ee882391c0dd392c28fa5", "generation_seconds_batch": 23.202503715991043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.661620616912842, "target_z": 4.3125002631177205, "ce": 6.133810997009277, "genuineness": 4.024092197418213, "identity": 0.6901257038116455, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "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_Teasing/c57bd96ae191b3fb271820caa7fd689e0986d960f62f368c1f332eb4b31df571.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "c66ee7fdf2afee5dcf71bcf3f34e8a54be40218af9559b608264944b4854423c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5818373d914dd43fc553f34fdeb3bc887af56bb0f1f905fa93adc4535ee4dac6", "generation_seconds_batch": 25.780122988973744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.165268898010254, "target_z": 1.5312500207724515, "ce": 6.205295085906982, "genuineness": 4.13078498840332, "identity": 0.5637029409408569, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c66ee7fdf2afee5dcf71bcf3f34e8a54be40218af9559b608264944b4854423c.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "c688efc88c5492058e9b30d7666bc3dcac2345ff613fcffe2b15062c0594273a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b3fb6367090b7c0594eae53b6c5de4e1a2c645a64629841ebee93a0fae229b05", "generation_seconds_batch": 23.93591421400197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8801887035369873, "target_z": 4.7187500346207525, "ce": 5.919358730316162, "genuineness": 4.036643981933594, "identity": 0.595647931098938, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c688efc88c5492058e9b30d7666bc3dcac2345ff613fcffe2b15062c0594273a.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "c6906cd04a967a7e78f9fe0d0a0a9d7f6404ec51df24994a93e88cea030b2e5a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "71745f93b1443ed08fc670980640c848e7250a1711b312c7e31980635c9f54f7", "generation_seconds_batch": 17.212999845971353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8079938888549805, "target_z": 0.8671874255653819, "ce": 6.308549880981445, "genuineness": 4.256305694580078, "identity": 0.6944602727890015, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c6906cd04a967a7e78f9fe0d0a0a9d7f6404ec51df24994a93e88cea030b2e5a.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "c769418ea16ad75acce51452f66ff84f6f31e500e3aa4cd969f5cdc0559c7bda", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2ba6885c197a0b0d4be2ec661258f09cf125ae6978109c6d450b477db162fc6a", "generation_seconds_batch": 24.666635148925707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8630058765411377, "target_z": 2.828125024234527, "ce": 6.41180419921875, "genuineness": 4.507347106933594, "identity": 0.6009791493415833, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c769418ea16ad75acce51452f66ff84f6f31e500e3aa4cd969f5cdc0559c7bda.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "c7c44f7926632cc7851ad6000a19fa6ce697754a4d77f84875bcda06177b8a64", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "abe51f399f2a4c8ca195cdbbb7cab4bac15251ec5240412c14cfc3de71d72e48", "generation_seconds_batch": 23.800618640030734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5267471075057983, "target_z": 2.203125051931129, "ce": 6.173524379730225, "genuineness": 3.8295347690582275, "identity": 0.29367753863334656, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c7c44f7926632cc7851ad6000a19fa6ce697754a4d77f84875bcda06177b8a64.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "c800f940104d795c4df8f6f072e8f033d0a88c48260de7b9e1ad49ac5dc9f008", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "95389ecb0191ff4eb4b45fcc569c0a15f14d24b6a0207cbc031899dc20aae32b", "generation_seconds_batch": 24.765801645000465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2665164470672607, "target_z": 3.578125079627731, "ce": 6.038498878479004, "genuineness": 3.9550557136535645, "identity": 0.5843547582626343, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c800f940104d795c4df8f6f072e8f033d0a88c48260de7b9e1ad49ac5dc9f008.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "f723731a9b5005832aac69b4aec4167647974a2889519f056099f290ae255842", "generation_seconds_batch": 19.7487087569898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8605343103408813, "target_z": 0.9648436504653362, "ce": 6.300607204437256, "genuineness": 4.362998008728027, "identity": 0.7628078460693359, "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_Teasing/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.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": "c85e6b340d71ab274b15b3987fe3cfbedea0ef84c30640362dfebce5c393cf54", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5fcecb1c8e82a5ab6ba97beb5c9939f1a1944baece115055699a36356d89342a", "generation_seconds_batch": 14.571391965961084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2497034072875977, "target_z": 3.546874892675667, "ce": 6.24500846862793, "genuineness": 4.262581825256348, "identity": 0.6152069568634033, "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_Teasing/c85e6b340d71ab274b15b3987fe3cfbedea0ef84c30640362dfebce5c393cf54.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "aba576f79c46b64b69af11ccd4af0b5374b9411d567831a3d74de5e0027005b3", "generation_seconds_batch": 15.303517808904871, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12076504528522491, "target_z": -0.4101562387482554, "ce": 6.316492557525635, "genuineness": 4.268857479095459, "identity": 0.3054978847503662, "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_Teasing/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "c8f142b509e03ea85e0c3f42d71af39f80ae8a0a3d1d1839e49df1e1a42f885e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0170eb3d3c6f9f93eecc1550f81aaa4b6620eb4caba43f661972aa5c5a065b6a", "generation_seconds_batch": 21.590204150998034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.762128233909607, "target_z": 2.6406250103862257, "ce": 5.7128496170043945, "genuineness": 3.6412534713745117, "identity": 0.43957898020744324, "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_Teasing/c8f142b509e03ea85e0c3f42d71af39f80ae8a0a3d1d1839e49df1e1a42f885e.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "c910eebebad719f719923838e0e1c8fc619ac77fa5c81feef0a48b71798754b3", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d1c3802a8067ab2b7892ae5b977a5de67a31df169ea8cc41e139f021b8c5076f", "generation_seconds_batch": 22.28255232097581, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9050382375717163, "target_z": 2.9062500484690537, "ce": 6.173524379730225, "genuineness": 4.074300289154053, "identity": 0.4426325559616089, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c910eebebad719f719923838e0e1c8fc619ac77fa5c81feef0a48b71798754b3.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "c94f8d7e7b8309771415b80445d54dbf7534d7539a328b6de9338cfe56adfcbb", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9538d86a01161b8bea21bd6a004a2a4f0322a1d2573f43244e2e2f7597427a4e", "generation_seconds_batch": 17.459966548951343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.333768129348755, "target_z": 3.7031249411447207, "ce": 6.332377910614014, "genuineness": 4.6705241203308105, "identity": 0.5368715524673462, "hypothesis": "Oh J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c94f8d7e7b8309771415b80445d54dbf7534d7539a328b6de9338cfe56adfcbb.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": "c954385a490f3cd12978093310a3ddb721deb2aa7312ee42c578cac61428c9fd", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "141272c9d490d39dc035bc4199ffc491423ac069be04de2791ee63d0512005bc", "generation_seconds_batch": 16.84618244203739, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7537217140197754, "target_z": 2.624999916910194, "ce": 6.213237762451172, "genuineness": 4.268857479095459, "identity": 0.6339360475540161, "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_Teasing/c954385a490f3cd12978093310a3ddb721deb2aa7312ee42c578cac61428c9fd.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "c98d5583668488e4a66de8a0f34001d960223c12c0004bf5000f135a9cabe5d7", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "64af7d67c7917797777a5e9092fc1d78fd71f9eb5aa068ab782a4c6132714d1f", "generation_seconds_batch": 17.28611433401238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.333768129348755, "target_z": 3.7031249411447207, "ce": 6.443574905395508, "genuineness": 4.243753433227539, "identity": 0.47535377740859985, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c98d5583668488e4a66de8a0f34001d960223c12c0004bf5000f135a9cabe5d7.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "c9d5e84695b18272d5470e000461ad7f529c33fc67047d0fbfa13c4e423233b5", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a9e742704ff39304903c92661f396dcbd71d7b9b2b79a76f54a87b5f3bd6b9ed", "generation_seconds_batch": 22.660532535985112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4679017066955566, "target_z": 2.093749840744538, "ce": 6.173524379730225, "genuineness": 3.8922953605651855, "identity": 0.5180796384811401, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c9d5e84695b18272d5470e000461ad7f529c33fc67047d0fbfa13c4e423233b5.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "c9ff229e9ab33c633790eedfef71be9cb4ef2aca110b433ea5e06ce30ecbbe32", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "a7dd8557c9afbb4b2e518a71778348edbc865df4a1eca0dfb609e5b36e44a028", "generation_seconds_batch": 25.581573706003837, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20903296768665314, "target_z": -0.2460937543275941, "ce": 5.998785495758057, "genuineness": 4.2751336097717285, "identity": 0.604406476020813, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/c9ff229e9ab33c633790eedfef71be9cb4ef2aca110b433ea5e06ce30ecbbe32.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "caa7d0bf4689c27011bf5d77679feeb87f3acaf54f8a35df3acaa8e489108a0a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3d79c8ec38bccbb885db599878bae5f5a891f8557c11cd89d74993ffe3bf42cf", "generation_seconds_batch": 18.127522705006413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8798187971115112, "target_z": 2.8593749896137743, "ce": 6.340320587158203, "genuineness": 4.281409740447998, "identity": 0.4882521331310272, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/caa7d0bf4689c27011bf5d77679feeb87f3acaf54f8a35df3acaa8e489108a0a.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "cb7e2521f80c3724350273c3fbec02c7d3bd3e7abb4aa7ebd7ae080b2b828521", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b941d284105b6599b8c4a17413d600c46d807a3b684c091964a8184e3af3ffaa", "generation_seconds_batch": 22.656764965038747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5726127624511719, "target_z": 0.429687467110285, "ce": 5.9431867599487305, "genuineness": 3.998987913131714, "identity": 0.5188694000244141, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/cb7e2521f80c3724350273c3fbec02c7d3bd3e7abb4aa7ebd7ae080b2b828521.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "cc0404762851df2e26f8c12fd4ab2bb1b6ececd918e7f78dfe27005ed84ac717", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "707bdb9e09173b2ca43a4936e3206fbf276cfabec39805d87e12cb7d529715fb", "generation_seconds_batch": 23.33181970496662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1232365369796753, "target_z": 1.4531249965379247, "ce": 6.2767791748046875, "genuineness": 3.7793264389038086, "identity": 0.3425813615322113, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/cc0404762851df2e26f8c12fd4ab2bb1b6ececd918e7f78dfe27005ed84ac717.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "cc28c7dfebafc46683f2a5317ad1e82e44f17d4ef69835d92dbb8385a7b3fbb7", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a38d5d64f50a334c65b60c6ea08a6e421d86f97af46eb250290fb9b0d58288c8", "generation_seconds_batch": 23.04378169903066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5435600280761719, "target_z": 2.2343750173103762, "ce": 6.284721851348877, "genuineness": 3.948779582977295, "identity": 0.384144127368927, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/cc28c7dfebafc46683f2a5317ad1e82e44f17d4ef69835d92dbb8385a7b3fbb7.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "cc4c6bc27da5b9570f2393183c2857daded7b7ae1ceef6802ff7abc1cd859227", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "039f5d51d94c09ea0aae755486cd3cb74407e21d4b251dfe61b86b47e0f5d0c4", "generation_seconds_batch": 21.544205259997398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2442350685596466, "target_z": -0.18066404930083804, "ce": 6.284721851348877, "genuineness": 4.570107460021973, "identity": 0.693190336227417, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/cc4c6bc27da5b9570f2393183c2857daded7b7ae1ceef6802ff7abc1cd859227.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "cc9b352fe845c73994bc468ef7504bef9f960d5d5d9bac5e1a7e15af0a6e5bac", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "988cc38b5d4981409095ec1e273ffc7d8e5ab9ccafa6859cc44d0df1566fc0bc", "generation_seconds_batch": 18.962152605992742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4598653316497803, "target_z": 3.937500235421118, "ce": 6.252951145172119, "genuineness": 4.243753433227539, "identity": 0.4772069752216339, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/cc9b352fe845c73994bc468ef7504bef9f960d5d5d9bac5e1a7e15af0a6e5bac.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "cde11aabc1dfb06609e9efe9c593af7c991f6ceadbb735c2a24b4de35daa1403", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fdfdec4639429492a124a9315b8abf490ce619cc1c2ca315506825341b7b77b9", "generation_seconds_batch": 17.65182835503947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5855923891067505, "target_z": 2.312500041544903, "ce": 6.300607204437256, "genuineness": 4.250029563903809, "identity": 0.2580355703830719, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/cde11aabc1dfb06609e9efe9c593af7c991f6ceadbb735c2a24b4de35daa1403.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "cde5c74f1a952349d88d2ef01453c844ea25dd9e219ef000a49b886db30eedd0", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3a4a2f6091312ceeb63e9787735a1ced6205f39449961050cf2806616004bd75", "generation_seconds_batch": 17.96266670501791, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6945065855979919, "target_z": 0.6562499930758495, "ce": 6.316492557525635, "genuineness": 4.570107460021973, "identity": 0.6451923847198486, "hypothesis": "He concrodeado 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_Teasing/cde5c74f1a952349d88d2ef01453c844ea25dd9e219ef000a49b886db30eedd0.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "ce02a3adb91f9392ed5da28daa87a039697ed74a758049945e768674cd9f0d11", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "445a633ceff7da0b6ab95a4844469f9f8f627f5daa8cb61b470dbac57affbf4b", "generation_seconds_batch": 26.51808729104232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.829379916191101, "target_z": 2.7656248719032153, "ce": 6.006728172302246, "genuineness": 3.6789097785949707, "identity": 0.40865370631217957, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie standen 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_Teasing/ce02a3adb91f9392ed5da28daa87a039697ed74a758049945e768674cd9f0d11.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "ce27b157b79d1e9f4b915f2e03c42ef1b7a66166e5853386164da0ce42185803", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "493ed129e36d7ef7436ba9ebbcf9386c873d2688a2e45364733bb040c4a7207e", "generation_seconds_batch": 26.338911270024255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1106268167495728, "target_z": 1.429687467110285, "ce": 6.23706579208374, "genuineness": 4.337893962860107, "identity": 0.6863600015640259, "hypothesis": "J'ai trouvé la 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_Teasing/ce27b157b79d1e9f4b915f2e03c42ef1b7a66166e5853386164da0ce42185803.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "ce457474e804f74bba2f940610b311357e6e579a53b850949b29db34236cb123", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c1aa447ab460eb6ea06f869fca7a05e857fef7463a314f8263c293c097662f6e", "generation_seconds_batch": 24.809552121092565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6251531839370728, "target_z": 0.5273436920102393, "ce": 6.125868320465088, "genuineness": 3.835810661315918, "identity": 0.7765618562698364, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ce457474e804f74bba2f940610b311357e6e579a53b850949b29db34236cb123.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "cf0c0ccf49890cc79987a8d0cb2a724c6d650009747fff5c04637d373df7e028", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9edcd7e0dd6dd2c14a7bb06c1f7af4a31e16ba5545bc854787d40cf0fbf59084", "generation_seconds_batch": 17.223058811970986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6864699125289917, "target_z": 2.4999998338203873, "ce": 6.229123115539551, "genuineness": 3.9299514293670654, "identity": 0.183757483959198, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/cf0c0ccf49890cc79987a8d0cb2a724c6d650009747fff5c04637d373df7e028.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "b98f12654872d5d2e13ed23c7cc92f01c44e934c9e3a22f2f09151e40617be3e", "generation_seconds_batch": 19.990066222962923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17435628175735474, "target_z": -0.31054687716379703, "ce": 6.38797664642334, "genuineness": 4.432034492492676, "identity": 0.6246600151062012, "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_Teasing/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "cfc9dcbad56ad3415fe8d242d620b2929b56a1679d416d0aa5be37215c4edbaa", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b774d74e992372bb0fc6f7d2a0a7d1a7d733a8ce2e20d434da95b7dddb774117", "generation_seconds_batch": 16.485860008979216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.434645891189575, "target_z": 3.8906251765658384, "ce": 6.252951145172119, "genuineness": 4.21237325668335, "identity": 0.5012897253036499, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/cfc9dcbad56ad3415fe8d242d620b2929b56a1679d416d0aa5be37215c4edbaa.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": "d098b2cd758e01b86f558e295ad2e0e08ff9f4f2d064787af35601dcec2df5bc", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4514dbc8d510dbef169a208737d5ec816a1c390c1962ea99bac85aa03f6a7145", "generation_seconds_batch": 18.423910591052845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6948764324188232, "target_z": 2.5156249272964195, "ce": 6.268836498260498, "genuineness": 4.243753433227539, "identity": 0.28171342611312866, "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_Teasing/d098b2cd758e01b86f558e295ad2e0e08ff9f4f2d064787af35601dcec2df5bc.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "56ebe81b798b50691dfa12cd86bd104883fc175257b486227bce71f0551694d9", "generation_seconds_batch": 16.90953200205695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09764724969863892, "target_z": -0.45312499653792476, "ce": 6.427689552307129, "genuineness": 4.20609712600708, "identity": 0.4072808027267456, "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_Teasing/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "7a774cd687865ea77352bfe6895bb969397c978f312412f9c0f8afc5a3d801d9", "generation_seconds_batch": 18.777087180060335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04510679841041565, "target_z": -0.5507812768310832, "ce": 6.475345611572266, "genuineness": 4.337893962860107, "identity": 0.43876034021377563, "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_Teasing/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "d2588e47bd9e19a11e60a3331ee09e3b910f04d083d7c0039740bc388a05131b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "28bff447f220aef3f24a17cafc0d7c0d18b05a2c371bfaba0e7643340b9327bb", "generation_seconds_batch": 26.621667413972318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0517815351486206, "target_z": 1.3203124774965107, "ce": 6.1894097328186035, "genuineness": 4.105680465698242, "identity": 0.5664318203926086, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d2588e47bd9e19a11e60a3331ee09e3b910f04d083d7c0039740bc388a05131b.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": "d2b3f67b4afdc25c1089506848343d72781fff1da14d00ebc9680f8d94b47d22", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c3fef5945a89a097a655367eb9656c234d7608c7238ad13b450c414082755134", "generation_seconds_batch": 23.30688981001731, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5099340677261353, "target_z": 2.1718748649790647, "ce": 6.348263263702393, "genuineness": 3.810706615447998, "identity": 0.38571181893348694, "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_Teasing/d2b3f67b4afdc25c1089506848343d72781fff1da14d00ebc9680f8d94b47d22.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "d2eb5722fa243b559b8f0dd6796838da2c01655e3b1471e016ed808c9e95ea57", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "943d4a31a941f5c30eb730095989b617e2c0b191fbd6e169ef470cd89d6735d1", "generation_seconds_batch": 25.84075599105563, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.610811710357666, "target_z": 2.359374878827366, "ce": 6.157639026641846, "genuineness": 4.3504462242126465, "identity": 0.4712779223918915, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d2eb5722fa243b559b8f0dd6796838da2c01655e3b1471e016ed808c9e95ea57.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "d347b2489a7e67e555e1468bb933b8253d0b14d8fb4d90e0a0c300d6e301c3b3", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "57a572bf7eaec6c8a20fa08f7c9aa8af70deb42ee020854eca76d011017ff711", "generation_seconds_batch": 23.792501399992034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3207886219024658, "target_z": 1.8203125882829192, "ce": 6.3641486167907715, "genuineness": 4.055472373962402, "identity": 0.45301902294158936, "hypothesis": "I found a little box. It was beside the old window. We can look inside together,", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d347b2489a7e67e555e1468bb933b8253d0b14d8fb4d90e0a0c300d6e301c3b3.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "7109547e6dbf5d4a9509e3488cdd448c9ecc325afe0452bfc56a93a78f46d4b0", "generation_seconds_batch": 20.567554222070612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26052260398864746, "target_z": -0.15039061071893953, "ce": 6.149696350097656, "genuineness": 4.400654315948486, "identity": 0.6763473749160767, "hypothesis": "J'ai écrit le numéro on l'enveloppe. Lis-le bien and verifie the two dernier chiffres. Appelle-moi quand tu auras a moment.", "wer": 0.3181818181818182, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.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": "d442dfc99e3139e326b23aa9a59bd1c76e91e7a249173ae72f3a045f285791a1", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c0e01d7c0f5492df520735b6a0ac4dad0f1fdc14d5320020c991d52520029e3c", "generation_seconds_batch": 28.62437602400314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4763082265853882, "target_z": 2.10937493422057, "ce": 6.308549880981445, "genuineness": 3.8169827461242676, "identity": 0.5832362174987793, "hypothesis": "Die Schlüsse liegen auf dem Küchentisch. Ich suchte in der Schublade, dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d442dfc99e3139e326b23aa9a59bd1c76e91e7a249173ae72f3a045f285791a1.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "d452fe91c8d0f8151eb8b0712433062d88f2d5a79938b929f2578693e8116f1b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b8c8b7e7b67a33c875e9e7962011b3337176d88225bbff6b97e9be58d93244d8", "generation_seconds_batch": 16.724185372004285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4426823854446411, "target_z": 2.046875003462075, "ce": 6.133810997009277, "genuineness": 3.9048471450805664, "identity": 0.49178260564804077, "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_Teasing/d452fe91c8d0f8151eb8b0712433062d88f2d5a79938b929f2578693e8116f1b.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "d4dcf71aade51ff8ec3cfd5ac5a130166746826168a493675b173697c6987e05", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1a373f7bbd2e9b9a5111e5614404f47d258a977bd9fa652857b006dc14281fee", "generation_seconds_batch": 23.135935576981865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.165268898010254, "target_z": 1.5312500207724515, "ce": 6.324435234069824, "genuineness": 4.256305694580078, "identity": 0.4461173117160797, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d4dcf71aade51ff8ec3cfd5ac5a130166746826168a493675b173697c6987e05.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "d50e3e0535947851cc47df86a879f6ca1bc96f3c819ba3bf86aa5ed9a8e6381d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2f5bb4964fc6c9f0422723c7c93f0089df6ee3780ba556f23273f0277a3969b2", "generation_seconds_batch": 25.84075599105563, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7032829523086548, "target_z": 2.5312500207724518, "ce": 6.157639026641846, "genuineness": 4.268857479095459, "identity": 0.6206531524658203, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d50e3e0535947851cc47df86a879f6ca1bc96f3c819ba3bf86aa5ed9a8e6381d.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "d53ec5ccc7c7459314d8c81701be9ae496c5af324c2ae803fca9884f2bd50b02", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6e95d04a73148c2c2d466250def55de1383bf527b1613e1ea351ff89062d8a13", "generation_seconds_batch": 27.078463296988048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.039541721343994, "target_z": 3.1562499930758494, "ce": 6.2767791748046875, "genuineness": 3.898571252822876, "identity": 0.5305486917495728, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d53ec5ccc7c7459314d8c81701be9ae496c5af324c2ae803fca9884f2bd50b02.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "d5566b5db7864d247accee1c9668f9e12a84a445c4c4ea62dad17f9f79ea5b33", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0496a66bbae19104d7d70c10c5989b8534814a5c08e4b9644469d3bc35f4e601", "generation_seconds_batch": 17.319545330945402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4218217134475708, "target_z": 0.14941402852838648, "ce": 6.316492557525635, "genuineness": 4.469690799713135, "identity": 0.618048906326294, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d5566b5db7864d247accee1c9668f9e12a84a445c4c4ea62dad17f9f79ea5b33.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "d6780717a850cb4211c715a7382953279db3994ff187916246359c897f212b73", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d09d31aece080bc9381b0da881ea30795e46093558eac1c42a232ad1a1f99702", "generation_seconds_batch": 19.775538335903548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0727977752685547, "target_z": 1.3593751004001826, "ce": 6.300607204437256, "genuineness": 4.293961524963379, "identity": 0.5663232803344727, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d6780717a850cb4211c715a7382953279db3994ff187916246359c897f212b73.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": "d680aab8f51aa26f301e09ac6aa82e8498914357083af2117c67142bcbdc5614", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e08bca79e56913f8fa8d9ecf44d9e7ff433ed12c550a41b3085ac6fea8d26937", "generation_seconds_batch": 18.682233405997977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4090564250946045, "target_z": 1.9843748511307637, "ce": 6.403861999511719, "genuineness": 4.300237655639648, "identity": 0.39812302589416504, "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_Teasing/d680aab8f51aa26f301e09ac6aa82e8498914357083af2117c67142bcbdc5614.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "d68913dc505d505545b248b31fe0af2c0123f0b7c906932262f2acede901eefe", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "4f10c6fb20992397ea953f868f3aab986781d0c276b837b964f47c01653dbff5", "generation_seconds_batch": 23.505177501938306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4423125088214874, "target_z": 0.18750001384830106, "ce": 6.284721851348877, "genuineness": 4.482243061065674, "identity": 0.3571387827396393, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d68913dc505d505545b248b31fe0af2c0123f0b7c906932262f2acede901eefe.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "d6956468b9ef9e3b6ee985e17f57d8f1b18bb1539ee9e6e4b1d34b68dfd9fc13", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "393c52c07e0416fe065f44437432d1bac20d007d1c7445b3b7d7d6e4bcec7d3b", "generation_seconds_batch": 26.689496601000428, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7785712480545044, "target_z": 0.8124999307584947, "ce": 6.165581703186035, "genuineness": 4.532451152801514, "identity": 0.7005677819252014, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d6956468b9ef9e3b6ee985e17f57d8f1b18bb1539ee9e6e4b1d34b68dfd9fc13.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "d6eb9fd22cd044ffe53557aaafd52f1b86914bcdd47cd361dfbfff5a479337fb", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c11f1a287bb1cc964021e3b1527f0242d2f4e2b5012fcce60cd536bd16df764b", "generation_seconds_batch": 24.809552121092565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6188483238220215, "target_z": 0.5156249272964194, "ce": 6.316492557525635, "genuineness": 4.21237325668335, "identity": 0.6169657707214355, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d6eb9fd22cd044ffe53557aaafd52f1b86914bcdd47cd361dfbfff5a479337fb.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "d71c7f7b8d36dfac57999feb935cf1fad98eff0f0bd40a279cef762d8f8c897f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "40b4037ffc028868803e43f390e5bdf8e0fcf8405f1019ba644032016c5d2365", "generation_seconds_batch": 24.35890205996111, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9004651308059692, "target_z": 1.0390625675104677, "ce": 6.23706579208374, "genuineness": 4.061748504638672, "identity": 0.41948774456977844, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d71c7f7b8d36dfac57999feb935cf1fad98eff0f0bd40a279cef762d8f8c897f.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "d7412d21078973e0e0e4b20483c7f388ddbe321d8394b45d312b08b030b76cd9", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "960128db3b2ce5c722ee5f2ba9d42082be90bd9e315e0d1a0d0840bd078c9403", "generation_seconds_batch": 25.090835456969216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08608835935592651, "target_z": -0.4746093615844584, "ce": 6.173524379730225, "genuineness": 4.268857479095459, "identity": 0.7056523561477661, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d7412d21078973e0e0e4b20483c7f388ddbe321d8394b45d312b08b030b76cd9.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "d752f8cbf0dbb6d6d808b8405209620de0722d833029e1c35222365289013fad", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2cf2cf737c23bd8a57ceb520af7ff0675cb9662851433ea4ebaa2cf817e8355e", "generation_seconds_batch": 23.544822718016803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49800536036491394, "target_z": 0.2910156211051653, "ce": 6.086154937744141, "genuineness": 3.973883628845215, "identity": 0.43854719400405884, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d752f8cbf0dbb6d6d808b8405209620de0722d833029e1c35222365289013fad.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": "d756f788f043a00ef6e6149fff233890ac1426a637d58111ff5b493ba8a57863", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1b210dd3713383cd58adba2b3b93ee9ffadec46e92bfa45fa667d03c479f9c79", "generation_seconds_batch": 20.86571554397233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7032829523086548, "target_z": 2.5312500207724518, "ce": 6.038498878479004, "genuineness": 4.011539936065674, "identity": 0.5693688988685608, "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_Teasing/d756f788f043a00ef6e6149fff233890ac1426a637d58111ff5b493ba8a57863.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "d787b949240c57a7b4fdb0f7be7f47b3f4be3b8ac91fe4f6914beb473683b1da", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b9d42e609fd550684503c478d2653e8043bfef823b95e82aed9159c45160b2fb", "generation_seconds_batch": 25.024828627938405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40500879287719727, "target_z": 0.11816406314913912, "ce": 6.459460258483887, "genuineness": 4.3504462242126465, "identity": 0.6114382147789001, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d787b949240c57a7b4fdb0f7be7f47b3f4be3b8ac91fe4f6914beb473683b1da.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": "d7bfbcc0c9ce5e45b3e45ff918db0bc751de7170e9d71d1b65a98971d20e78eb", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c0e32fffe69b7a9227aca262e9b355dd5c6f2fce3dae692826bf6e03c5a2575a", "generation_seconds_batch": 16.84618244203739, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8542295694351196, "target_z": 0.9531251073243332, "ce": 6.340320587158203, "genuineness": 3.9048471450805664, "identity": 0.44904112815856934, "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_Teasing/d7bfbcc0c9ce5e45b3e45ff918db0bc751de7170e9d71d1b65a98971d20e78eb.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "d8799a00c11ad8720a54e5b5eb7462bdce89d5a5b1405dc2b2b7f6e67c72f828", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d4f6c421d837ee73f65ad161f604ed2957156b0d2bd3b1bbc7122ae037f48a79", "generation_seconds_batch": 25.38431250897702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.354414463043213, "target_z": 1.882812519041414, "ce": 6.324435234069824, "genuineness": 3.9173994064331055, "identity": 0.3701015114784241, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d8799a00c11ad8720a54e5b5eb7462bdce89d5a5b1405dc2b2b7f6e67c72f828.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "d8b33ac6913d5b8d7e8e50ff300fe6ea2b010d97f5b7eeeac531ad68886e3489", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9c07fb59a28ead5257e2d813b024db487c20786688ff0ab293304d9c4a8242ba", "generation_seconds_batch": 22.476197196054272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6528440713882446, "target_z": 2.4374999030618927, "ce": 5.824047088623047, "genuineness": 4.174716949462891, "identity": 0.4851981997489929, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d8b33ac6913d5b8d7e8e50ff300fe6ea2b010d97f5b7eeeac531ad68886e3489.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": "d8f6616b8056ddb4171c5d14edd41778d374a25386cf606edfa30042c0a40a40", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "293d65a7fa18f0101be0803dd5d5e434ddc0941c32ac122cb4131933d83f967a", "generation_seconds_batch": 18.67624744796194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4763082265853882, "target_z": 2.10937493422057, "ce": 6.165581703186035, "genuineness": 4.162164688110352, "identity": 0.6715983152389526, "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_Teasing/d8f6616b8056ddb4171c5d14edd41778d374a25386cf606edfa30042c0a40a40.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "d90a81c0310ede2e85f28b34ae2dbe92d2b7ae6696f8cc233add96601eee2dda", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "23b69a1fa9dcf2a25959c9f8350dcf2cba3608022c4f7d201fdffb4baa19bdc7", "generation_seconds_batch": 17.584697530954145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1862850189208984, "target_z": 1.5703124221033065, "ce": 6.181467056274414, "genuineness": 4.193545341491699, "identity": 0.651889979839325, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d90a81c0310ede2e85f28b34ae2dbe92d2b7ae6696f8cc233add96601eee2dda.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "d98845fa847673b0bf5061e128fc862b84a647819a9bb464b72dbb15dc70a6d4", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6f1a9ae6c6f38dd4bd82b04c9feb879a8580e1d70d85f8c103639303b33922f0", "generation_seconds_batch": 16.724185372004285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7116893529891968, "target_z": 2.546874892675667, "ce": 6.197352409362793, "genuineness": 4.049196243286133, "identity": 0.46309036016464233, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d98845fa847673b0bf5061e128fc862b84a647819a9bb464b72dbb15dc70a6d4.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "d99b8066d00e4c6c6aa55c8efa154516f751fd6b58e723fd8f8481e81387cb9a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f2c7c5c37be8ae691708af527291879dd3b58cf958024d6aba556e976d02642f", "generation_seconds_batch": 24.330598721047863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1232365369796753, "target_z": 1.4531249965379247, "ce": 6.006728172302246, "genuineness": 4.137060642242432, "identity": 0.6315370798110962, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d99b8066d00e4c6c6aa55c8efa154516f751fd6b58e723fd8f8481e81387cb9a.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "d9fa7b791a341b75140ba85e760070043eeed15ade1d43e75be41aa2f85ea555", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5e8e9812d86293c707bf5e7f2d5ebcd3adb5f538ce909f86e9fcad5fe997f6e9", "generation_seconds_batch": 22.28255232097581, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7116893529891968, "target_z": 2.546874892675667, "ce": 6.078212261199951, "genuineness": 3.848362922668457, "identity": 0.5956809520721436, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vija. ¿Podemos mirar juntas?", "wer": 0.35294117647058826, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/d9fa7b791a341b75140ba85e760070043eeed15ade1d43e75be41aa2f85ea555.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "da5f40c581e755b769536f8654ab816cfd8938fbd9a7d119af63c268dca39b11", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7c5469af3781bc06072796696432aa73835f4ca2f32dc703f02c2840ea5f25b8", "generation_seconds_batch": 17.233040251070634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7806729078292847, "target_z": 0.816406259520707, "ce": 6.3641486167907715, "genuineness": 4.055472373962402, "identity": 0.6183154582977295, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinaus.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/da5f40c581e755b769536f8654ab816cfd8938fbd9a7d119af63c268dca39b11.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "da9507153db77d088a99f18b834724442d2ff448cd4a925211f9339c4fed66ec", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "1c16a351f1eb372a0546022b8788e075647ae1736510eab6ab6d8456c5061983", "generation_seconds_batch": 18.823554044007324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2328906059265137, "target_z": 3.5156251488692365, "ce": 6.038498878479004, "genuineness": 4.049196243286133, "identity": 0.5934901237487793, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/da9507153db77d088a99f18b834724442d2ff448cd4a925211f9339c4fed66ec.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "dabc58180b857a1a7106c8d5204840d8c65c8568355ce8ea9c3b4ce315ca4383", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "516068ca22cc8fe2f4e531b5604f3824bf45e6ee33c6044bec7a460ba8d9798b", "generation_seconds_batch": 17.146719772019424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7789411544799805, "target_z": 2.671874975765473, "ce": 6.38797664642334, "genuineness": 3.773050308227539, "identity": 0.396637499332428, "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_Teasing/dabc58180b857a1a7106c8d5204840d8c65c8568355ce8ea9c3b4ce315ca4383.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "dad426ac0e1192c1eeb41f599524bffb4ee5f9ee42b3e9a24465e7bbe85770a0", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3bdefaf0cffeb0f56cf39842695a910e5690dd579ed34c10354c44fe195f2b8c", "generation_seconds_batch": 23.367534690070897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.989102840423584, "target_z": 3.0624998753652903, "ce": 6.141753673553467, "genuineness": 4.042920112609863, "identity": 0.47962474822998047, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/dad426ac0e1192c1eeb41f599524bffb4ee5f9ee42b3e9a24465e7bbe85770a0.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "7e257bc3a9709196a6563ac636a697d7a87cf064d41866ee09e6d576a06a69fc", "generation_seconds_batch": 16.87453493999783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15859414637088776, "target_z": -0.3398437612517446, "ce": 6.395919322967529, "genuineness": 4.231201171875, "identity": 0.33125603199005127, "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_Teasing/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "dbbe05fd20065468374914722916b9dd7168d5285f9580868b580a6220231a06", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7fb1ee7d006c9f92f88e4dc2624a8ce8f76b6e89d71c729624be0d50a5829d4a", "generation_seconds_batch": 25.780122988973744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1484559774398804, "target_z": 1.5000000553932042, "ce": 6.229123115539551, "genuineness": 4.049196243286133, "identity": 0.7850472331047058, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/dbbe05fd20065468374914722916b9dd7168d5285f9580868b580a6220231a06.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "dbf0e8a1a66a0dc1771b792bbea75c08d3a645f13a6939fdfd2d2170a3c7b253", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "cb361ee6726b12923912aa676483c5be1cdba8451ac6f96f71adeac253864abc", "generation_seconds_batch": 24.24869817995932, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9382941722869873, "target_z": 1.1093749342205699, "ce": 6.070269584655762, "genuineness": 4.218649387359619, "identity": 0.5938352346420288, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen het er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/dbf0e8a1a66a0dc1771b792bbea75c08d3a645f13a6939fdfd2d2170a3c7b253.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "dcd052faef7a2a0428fddc27fe35a0aa665cb9972fdd8f4e743dece06516e98b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f32389a970e67be07d2ae22002def0ebe65e0928f65e3abd938d012a28456b99", "generation_seconds_batch": 23.247760772006586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6696569919586182, "target_z": 2.4687498684411397, "ce": 6.24500846862793, "genuineness": 4.394378662109375, "identity": 0.6380763649940491, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/dcd052faef7a2a0428fddc27fe35a0aa665cb9972fdd8f4e743dece06516e98b.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "dce3b6426c3d6da0b001817bcee5efd882ae131d4bbfb5f71ba67dd7072278a7", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c959e61079b28990fd898ae1308119ed340403a7908f0d69124fd742bda78f36", "generation_seconds_batch": 23.193881009006873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5855923891067505, "target_z": 2.312500041544903, "ce": 6.340320587158203, "genuineness": 4.118232727050781, "identity": 0.4022534489631653, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/dce3b6426c3d6da0b001817bcee5efd882ae131d4bbfb5f71ba67dd7072278a7.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "dd0f860a941177fec0a2677df528b55af881485cf13763b19c62229e31b03956", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "73851ac393afa9ed79df46a9de1b497b4a08de97bb6dc8094eed2e11eed62999", "generation_seconds_batch": 16.703919474966824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5435600280761719, "target_z": 2.2343750173103762, "ce": 6.0146708488464355, "genuineness": 3.873466968536377, "identity": 0.44239097833633423, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/dd0f860a941177fec0a2677df528b55af881485cf13763b19c62229e31b03956.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "dd7717c00f6f087be441eb33db22f6f28ab6c6121d2e447e22310cd9753f688e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e1cdf5baade13de003ce672167e9e8b251ce5d754653ec1ff3514d7291555ffe", "generation_seconds_batch": 22.0687438279856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5603729486465454, "target_z": 2.2656249826896238, "ce": 6.062326908111572, "genuineness": 4.080576419830322, "identity": 0.5483757853507996, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/dd7717c00f6f087be441eb33db22f6f28ab6c6121d2e447e22310cd9753f688e.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "dd77fcd50c534fb5ffcaf8c3e5f33cbe37e83d259aeace312293a12d01f95a45", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b9d2b395479a9bf88d9790c99211ebf11feb0aae47e8d1ee280268c225fd31bb", "generation_seconds_batch": 23.158856668975204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3333982229232788, "target_z": 1.843749896137742, "ce": 6.324435234069824, "genuineness": 3.923675537109375, "identity": 0.5138664245605469, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/dd77fcd50c534fb5ffcaf8c3e5f33cbe37e83d259aeace312293a12d01f95a45.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": "dd98250a1a27ac0a1795cf6b0a0e606acb1e809b15bd7ddfd1498f0806792c27", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2237b094e7f7b953770fce26935c2a07532769eddee75b6d760bedac1397f975", "generation_seconds_batch": 14.928362309001386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1820818185806274, "target_z": 1.562499986151699, "ce": 6.165581703186035, "genuineness": 4.15588903427124, "identity": 0.34184443950653076, "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_Teasing/dd98250a1a27ac0a1795cf6b0a0e606acb1e809b15bd7ddfd1498f0806792c27.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "ddbf2ed7004e144185593dfb15e1e29313619cdfc53b6abf52ab186a2b0cc8bc", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "40ad270cd07eb6f5e4bb66b878c67f72f4d85ed617d91dfe392496a6e32b605e", "generation_seconds_batch": 22.3555892650038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.762128233909607, "target_z": 2.6406250103862257, "ce": 6.2767791748046875, "genuineness": 4.111956596374512, "identity": 0.4498971104621887, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ddbf2ed7004e144185593dfb15e1e29313619cdfc53b6abf52ab186a2b0cc8bc.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "ddcc36f172d7dfbc00581be7d5cef6d413054ffed43e27fcf8c67e05ceb4be18", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3f9e30aeab7dc7ab293cdd4c65ad7f62d1ea4fb39f432cc80385be3ceb2798c7", "generation_seconds_batch": 22.576886569033377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8714122772216797, "target_z": 2.843749896137742, "ce": 6.1894097328186035, "genuineness": 3.6789097785949707, "identity": 0.5595850348472595, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ddcc36f172d7dfbc00581be7d5cef6d413054ffed43e27fcf8c67e05ceb4be18.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "de006e4bf01758176a836908dc36ad6c0d291505f5e7e4603fc60dbabeeee983", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a033ffa170569f368629a20ff45c83b275c164ecc11ee91b0b6fab9731cf7485", "generation_seconds_batch": 24.34862036490813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7032829523086548, "target_z": 2.5312500207724518, "ce": 6.022613525390625, "genuineness": 3.528284788131714, "identity": 0.5447105169296265, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/de006e4bf01758176a836908dc36ad6c0d291505f5e7e4603fc60dbabeeee983.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "de2973be7892b0329c60e471cd67df8a81c2dd73a9af48848ebf3c4e152773cb", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f78d76b60dbd4924f28603e17778f4e29d3dcbd011cbd48a45c49abce878ba08", "generation_seconds_batch": 23.428753401967697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17750871181488037, "target_z": -0.3046874948068871, "ce": 6.1020402908325195, "genuineness": 4.15588903427124, "identity": 0.5569349527359009, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/de2973be7892b0329c60e471cd67df8a81c2dd73a9af48848ebf3c4e152773cb.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "deb9803f9ff07752a578c85a497a3c6c89a181aeabcea27b2372cc23992ea746", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ef8039187be44a3b38e7510ae0fb66fcd85a4924b421d621fa342506700a62b6", "generation_seconds_batch": 18.465325520024635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3754305839538574, "target_z": 1.921874920372269, "ce": 6.165581703186035, "genuineness": 4.005263805389404, "identity": 0.29392576217651367, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/deb9803f9ff07752a578c85a497a3c6c89a181aeabcea27b2372cc23992ea746.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "deda836f601ba71f6c1948ac45a12b346c3c06e5f4ac8ff814aaeb6e23c43a05", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5d13b1bb56693e6e36f770d5089fc772cdf28e3407dbb5bf10d6522b7e0d3499", "generation_seconds_batch": 17.068793882033788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8041605949401855, "target_z": 2.7187500346207525, "ce": 5.998785495758057, "genuineness": 3.660081624984741, "identity": 0.4307763874530792, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemein!", "wer": 0.125, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/deda836f601ba71f6c1948ac45a12b346c3c06e5f4ac8ff814aaeb6e23c43a05.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "dfcb0aba7828b7bad2ca7e48e778768f09f464c81da62e1e131f8f73576ee720", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "486cebc83ab56ab2ba5300264de21c6aaba1d1e424de7e9a74d11c88ed8aca7e", "generation_seconds_batch": 25.87462053494528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2367238998413086, "target_z": 1.6640625398138655, "ce": 6.252951145172119, "genuineness": 3.8922953605651855, "identity": 0.32683318853378296, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/dfcb0aba7828b7bad2ca7e48e778768f09f464c81da62e1e131f8f73576ee720.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "dfe484b191c09fbce8c890c3910c9d86be077bf12f315cb0a66fe603ad1a0550", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "989f8b4cee2af644dfcae5546b16ce52ccd482d376f565257beafcdf0775b2ad", "generation_seconds_batch": 20.01463947596494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.678433418273926, "target_z": 4.34375000692415, "ce": 6.117925643920898, "genuineness": 3.8671910762786865, "identity": 0.7961878776550293, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/dfe484b191c09fbce8c890c3910c9d86be077bf12f315cb0a66fe603ad1a0550.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "dfed1a0b4c73a68ec5892952873caa5c6b191c875339096489f634b9addfa909", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cee155fd0f9fe48087e5e995eb6aef5c3145878cc843fb5dccc906cf76257604", "generation_seconds_batch": 23.193881009006873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4675319194793701, "target_z": 0.23437501731037633, "ce": 6.260893821716309, "genuineness": 4.118232727050781, "identity": 0.30035531520843506, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/dfed1a0b4c73a68ec5892952873caa5c6b191c875339096489f634b9addfa909.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "e034e89ea9e7ddf6970fb3cbc80a14f1637970400551c89334d5e52443b9b42e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8383d28a5019b7c70bc07de60bba256f7fd466f5db0ba4b6c005e00369406a23", "generation_seconds_batch": 23.043383026029915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2577400207519531, "target_z": 1.7031249411447205, "ce": 6.09409761428833, "genuineness": 4.2374773025512695, "identity": 0.6936694383621216, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e034e89ea9e7ddf6970fb3cbc80a14f1637970400551c89334d5e52443b9b42e.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "e116e7e86226d36ca6b05a2f647b652a2d59c0fad565b5598f691acb159fa664", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "97af56256ada8d846a58154554faa2a9748ccb4394b971b0d586073a448a9ea0", "generation_seconds_batch": 24.23947368899826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1236064434051514, "target_z": 3.312500041544903, "ce": 6.141753673553467, "genuineness": 4.218649387359619, "identity": 0.5782609581947327, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e116e7e86226d36ca6b05a2f647b652a2d59c0fad565b5598f691acb159fa664.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "e1f8f57b2d6de8a555e00c8db430cb62a0af7a1ea5992b43280030c78f0ac52d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "426372cfbcae1a617a91ba03c6872f307b4d1444bd1a71c92230ad32caceb90b", "generation_seconds_batch": 24.990077211055905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6192182302474976, "target_z": 2.374999972303398, "ce": 6.308549880981445, "genuineness": 4.331617832183838, "identity": 0.6338863372802734, "hypothesis": "Je trouvais la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e1f8f57b2d6de8a555e00c8db430cb62a0af7a1ea5992b43280030c78f0ac52d.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "e240c4272b98569450102338c289a62239593787d9beb4b5c9d64abe83b53c0d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "95e908426cd93b07731235c878a09380862d7fcc18bf51c9d6a67ee270908e17", "generation_seconds_batch": 23.548563453019597, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8545993566513062, "target_z": 2.8124999307584946, "ce": 6.252951145172119, "genuineness": 3.6789097785949707, "identity": 0.252080500125885, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e240c4272b98569450102338c289a62239593787d9beb4b5c9d64abe83b53c0d.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "e490ae8415028e18b52325ab7a204f5be09f57c846ab1753c2537d007006b52e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "57faa6c2e5641b45a5bab5a9d269583ad82ffdbec4c2f2a4db1b26d08a42dd46", "generation_seconds_batch": 16.80015004402958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.417462944984436, "target_z": 1.9999999446067958, "ce": 6.268836498260498, "genuineness": 4.268857479095459, "identity": 0.3706699013710022, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e490ae8415028e18b52325ab7a204f5be09f57c846ab1753c2537d007006b52e.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "e4d261fdf2a27d28b0f4d2b867b3bb631972997b2ec92b152623f74be20bba51", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f4007e63243dbd87eb4d36cc82513f44fc6876e1f15493c700a0230c1abb3349", "generation_seconds_batch": 22.39246042596642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5855923891067505, "target_z": 2.312500041544903, "ce": 6.252951145172119, "genuineness": 4.381826400756836, "identity": 0.5134037733078003, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e4d261fdf2a27d28b0f4d2b867b3bb631972997b2ec92b152623f74be20bba51.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "e4e48a11e361259977083a7fb4262672df24fee5f07f8ba0b5358644a3fb96c3", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "af3a0f4db5316920278657e904475356c1affeae68030d65c49373b52c736654", "generation_seconds_batch": 21.95834291097708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5099340677261353, "target_z": 2.1718748649790647, "ce": 6.062326908111572, "genuineness": 4.105680465698242, "identity": 0.679641604423523, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e4e48a11e361259977083a7fb4262672df24fee5f07f8ba0b5358644a3fb96c3.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "e54acc50b7f8c8bd3f9c7c1a4611c40ad059603735f34fc92087a64abdd21eb9", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "100215221981042d0006860c3a9516b41e051f92cf8facdf399d1b8efe878936", "generation_seconds_batch": 24.56675198196899, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2871626615524292, "target_z": 1.7578124359516076, "ce": 6.316492557525635, "genuineness": 4.137060642242432, "identity": 0.25802236795425415, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e54acc50b7f8c8bd3f9c7c1a4611c40ad059603735f34fc92087a64abdd21eb9.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "e5c04eacab1fc31ffe2aba8ed6226c60a43eb0471e4cf35117531a6fc1762e38", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3db70bea2cf7809c1f3535a4fff8dd772eeaac2d0084c281c0a931012722dac9", "generation_seconds_batch": 23.1091592409648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9638835191726685, "target_z": 3.015625038082828, "ce": 6.0305562019348145, "genuineness": 4.068024158477783, "identity": 0.6649088263511658, "hypothesis": "De deur staat nog open. Ik heb je juist op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e5c04eacab1fc31ffe2aba8ed6226c60a43eb0471e4cf35117531a6fc1762e38.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "e623055f880a9ef5698e2caaa8df2b27b01f1b0d608ceeba9639bea0e7c6c859", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "124eaaa39f6742cdc78b45cbc766e32fe36025939ad1d2989560826afe6ef13c", "generation_seconds_batch": 18.919154611998238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3207886219024658, "target_z": 1.8203125882829192, "ce": 6.205295085906982, "genuineness": 3.8420867919921875, "identity": 0.1567455679178238, "hypothesis": "Le 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_Teasing/e623055f880a9ef5698e2caaa8df2b27b01f1b0d608ceeba9639bea0e7c6c859.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": "e66628b40595c91f415b4481a0e9371d82c1e4fdadf16591a2876d8e54686b99", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f4b59b3eb7519be1a6c1383a41fecd0862c8d078a16c93ac425bb23b918ef2d3", "generation_seconds_batch": 17.144092753063887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8041605949401855, "target_z": 2.7187500346207525, "ce": 6.23706579208374, "genuineness": 4.494794845581055, "identity": 0.6829886436462402, "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_Teasing/e66628b40595c91f415b4481a0e9371d82c1e4fdadf16591a2876d8e54686b99.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "989bf267e13bea9774636b654be40ca967d2a817b112db0b0a7430baf7abd63b", "generation_seconds_batch": 15.303517808904871, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08398672938346863, "target_z": -0.4785156349534664, "ce": 6.348263263702393, "genuineness": 4.419482707977295, "identity": 0.3567163348197937, "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_Teasing/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.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": "e6fd63f6c016cde167ae7b0afa4906efd703b56848199387edcd53022beacf34", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e9b7c1f142a42384bd480a60b3cadf86da576d6da0a07b664f563000d9672221", "generation_seconds_batch": 28.608841360080987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2412970066070557, "target_z": 3.5312500207724518, "ce": 6.23706579208374, "genuineness": 3.8044304847717285, "identity": 0.5806068181991577, "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_Teasing/e6fd63f6c016cde167ae7b0afa4906efd703b56848199387edcd53022beacf34.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "e7298d13ca988f5bc08101301f1390e54a5234c80dc3c39a4f6e157866f9b32e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b0e0db3959718b64468eb9cb6927ad18f1fcb43da2083fe1871b50729b89ee78", "generation_seconds_batch": 17.973106472054496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6444376707077026, "target_z": 2.4218750311586774, "ce": 6.324435234069824, "genuineness": 3.7918784618377686, "identity": 0.6175990700721741, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e7298d13ca988f5bc08101301f1390e54a5234c80dc3c39a4f6e157866f9b32e.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "e7bdb550f74b380e8f9fde7bc0f83cf24b270c25661da58fb4feb9e80adce905", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a74e098e26ce401ea3c5166d20c73df09c9916a2a356231de0629e5c965cec7d", "generation_seconds_batch": 23.288150364998728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9722899198532104, "target_z": 3.0312499099860433, "ce": 6.197352409362793, "genuineness": 4.2249250411987305, "identity": 0.17055419087409973, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e7bdb550f74b380e8f9fde7bc0f83cf24b270c25661da58fb4feb9e80adce905.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": "e7e179d51f86b62baed615bcf583e868c31f8f3587fbb1ff1a3a121ee157842a", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7cd1bd15d06f35f84c2f5bd27efb9efd5d09f46b22000dca08eda153a6fda881", "generation_seconds_batch": 25.649903555982746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.745685338973999, "target_z": 4.468750311586774, "ce": 6.3641486167907715, "genuineness": 4.13078498840332, "identity": 0.6699323654174805, "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_Teasing/e7e179d51f86b62baed615bcf583e868c31f8f3587fbb1ff1a3a121ee157842a.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "e8183a86b458b0ca2d62e42a29f3f1824e4d0ced6eaa5171fb049d8bb0e9eb35", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "38f319dc0f1abfb7b107b05c83efbef18be0352ec674ee58c6ee5bb35cc2a3f0", "generation_seconds_batch": 25.024828627938405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8920586109161377, "target_z": 1.0234374740344354, "ce": 6.427689552307129, "genuineness": 3.8922953605651855, "identity": 0.3926301598548889, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e8183a86b458b0ca2d62e42a29f3f1824e4d0ced6eaa5171fb049d8bb0e9eb35.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "e8520f67f1cff907b94577a83a99b05aa8a4e113dc50a355157f89b76b41232d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "028bde8171ec5c5a76e65b4931eaf4231c0dd81fb043bb712d6670abd3bf6a5f", "generation_seconds_batch": 23.1816362059908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9719201326370239, "target_z": 1.1718750865518817, "ce": 6.2767791748046875, "genuineness": 4.3127899169921875, "identity": 0.5333385467529297, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e8520f67f1cff907b94577a83a99b05aa8a4e113dc50a355157f89b76b41232d.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "e8cb23fa5efa285ae4f1e2be8a7c32406448386de5de96a68eacb9dadb03963a", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c09ded30232129675d80dc3b43aba33926ac3fc128441ce7919711de278a60a8", "generation_seconds_batch": 23.70765515801031, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.02272891998291, "target_z": 3.125000249269419, "ce": 5.967014789581299, "genuineness": 4.432034492492676, "identity": 0.5928488969802856, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We've regarded ensemble what contien.", "wer": 0.3157894736842105, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e8cb23fa5efa285ae4f1e2be8a7c32406448386de5de96a68eacb9dadb03963a.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "e90656f1362bccc93939c6094af8a18d57511bd275268466da9d917ebccdc86e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "47e2ebca4fddb67fb3e774121fbeaefe02e713643610f55abd0e86f49f438793", "generation_seconds_batch": 24.478151728981175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4090564250946045, "target_z": 1.9843748511307637, "ce": 5.982900142669678, "genuineness": 4.086852550506592, "identity": 0.6252623796463013, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e90656f1362bccc93939c6094af8a18d57511bd275268466da9d917ebccdc86e.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": "e92ef09b3c5da9af12f874a6e415020e3a63bd01b3318eb23b5c95fa69dbff2d", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "08b76122b9b1bb16c22b7a9c22b8c7ecb315c4f1823d7bbd261838e988293534", "generation_seconds_batch": 24.129037444014102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7029130458831787, "target_z": 0.6718749757654732, "ce": 6.181467056274414, "genuineness": 4.074300289154053, "identity": 0.676791787147522, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-le bien and verify the two dernier chiffres. Appelle-moi quand tu aurais aimé.", "wer": 0.36363636363636365, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e92ef09b3c5da9af12f874a6e415020e3a63bd01b3318eb23b5c95fa69dbff2d.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "e93bf2754a414b5e318bd31235cc0bafd36b93f3459657b1a4af747e02ff1f64", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a5a3e726d915afd9dffff0992e1f000236ff3eed2f3daaf22d29e78a02696e0a", "generation_seconds_batch": 23.852204752038233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3712273836135864, "target_z": 1.9140624844206613, "ce": 5.967014789581299, "genuineness": 4.2374773025512695, "identity": 0.5408492088317871, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e93bf2754a414b5e318bd31235cc0bafd36b93f3459657b1a4af747e02ff1f64.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "e95858210282b4379448a907ebf7ea4f64a0017173e29bc977b746d7da6b8387", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0c6620764a2f96ac37f80426162ea1e0c792aaeb9055bb044df65949a092b5ea", "generation_seconds_batch": 19.775538335903548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1190333366394043, "target_z": 1.445312560586317, "ce": 6.308549880981445, "genuineness": 3.9676074981689453, "identity": 0.4250010848045349, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e95858210282b4379448a907ebf7ea4f64a0017173e29bc977b746d7da6b8387.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "e9836c84fb407fbd953446ac1bb539d23a86b077d219fc2227a09b43eaaf61c6", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9374a640102941e619e3cb88bec059ba9b923b128c363ef7c95b866d67500537", "generation_seconds_batch": 23.841643725987524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0563547611236572, "target_z": 3.187500180027914, "ce": 6.141753673553467, "genuineness": 3.873466968536377, "identity": 0.42969372868537903, "hypothesis": "I found the little bug. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e9836c84fb407fbd953446ac1bb539d23a86b077d219fc2227a09b43eaaf61c6.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "e9b100095a439d0e764134a2a25ed3e38e79083534542e608f9b928c2dd9cdfd", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f54c75d5dcb7628ecce2b0b2942eb423bfddd11a3e064923c7def818f1d2b46b", "generation_seconds_batch": 16.31573352299165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.30854868888855, "target_z": 3.656249882289441, "ce": 5.816103935241699, "genuineness": 3.9299514293670654, "identity": 0.629036545753479, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e9b100095a439d0e764134a2a25ed3e38e79083534542e608f9b928c2dd9cdfd.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "e9d0876ba2b706320648ef0c8e9da0dbaba230cd27413b4b624bdf57956eca64", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "997f4b433ca567a59e9c3ab89c6de98d7418cc5bbb8f5c4d072c4e41b99f7699", "generation_seconds_batch": 15.692940325010568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.723929226398468, "target_z": 0.7109374878827366, "ce": 6.332377910614014, "genuineness": 4.6203155517578125, "identity": 0.6123349666595459, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e9d0876ba2b706320648ef0c8e9da0dbaba230cd27413b4b624bdf57956eca64.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "eb9b61eddf2349de394e0ad820685bf9c767cd3bcbcc2126b354ab790c107fd2", "generation_seconds_batch": 19.990066222962923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08188512921333313, "target_z": -0.4824218529292702, "ce": 6.427689552307129, "genuineness": 4.607763767242432, "identity": 0.4790111184120178, "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_Teasing/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "e9eb836e0a18f64faa8e4263509afed65eeefbd289181cc38f5c841e05ec0ce6", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "dea23ce2760d01c24804baa1f4ab417c32473f91a33f3952344b2d264d4bd76e", "generation_seconds_batch": 22.252084524021484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9302575588226318, "target_z": 2.9531248857515164, "ce": 6.149696350097656, "genuineness": 4.3127899169921875, "identity": 0.4684242308139801, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/e9eb836e0a18f64faa8e4263509afed65eeefbd289181cc38f5c841e05ec0ce6.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "ea5e88425cf801303c3e59d86147d29567da1806568704b6ac595df24b4278c0", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "431b4d4d67c3dc6429d8fe73c5314eea6a52a7ba0806effed384ce40687925c6", "generation_seconds_batch": 23.78086079796776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5607428550720215, "target_z": 4.125000027696602, "ce": 6.109982967376709, "genuineness": 3.5596652030944824, "identity": 0.27252131700515747, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ea5e88425cf801303c3e59d86147d29567da1806568704b6ac595df24b4278c0.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "ea603ad7b5e02d2d4f839e740c88040356ac7a2f1c4bd89326be2d8009d764b2", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e0ca6b6997540d816ad96af1aaedd8d5a9540b7f39830ed599fcafa6c340b299", "generation_seconds_batch": 17.41001522995066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9638835191726685, "target_z": 3.015625038082828, "ce": 6.260893821716309, "genuineness": 3.923675537109375, "identity": 0.2770705223083496, "hypothesis": "I found the little box. It was beside the o window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ea603ad7b5e02d2d4f839e740c88040356ac7a2f1c4bd89326be2d8009d764b2.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "ead384fd906eafebeb091423961c218cedd2ea16ea39d9d4ba2ba1da7d4bdd63", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "478c9e4627493f0c744cc9dc138d44ec2ecded1e9a7a43f0c7b5b8207cc28ed8", "generation_seconds_batch": 17.329807152971625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5267471075057983, "target_z": 2.203125051931129, "ce": 6.308549880981445, "genuineness": 3.8044304847717285, "identity": 0.34300506114959717, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ead384fd906eafebeb091423961c218cedd2ea16ea39d9d4ba2ba1da7d4bdd63.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": "eb891e47f8ed522f6fa79affef524468d1567b6c61997fbf24bced6f02351b84", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "211fc6a2e68ac755a2765085520d925dec0c934f431a9fcfeed58727fd5885f9", "generation_seconds_batch": 17.160850384971127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.039541721343994, "target_z": 3.1562499930758494, "ce": 6.308549880981445, "genuineness": 4.055472373962402, "identity": 0.6427979469299316, "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_Teasing/eb891e47f8ed522f6fa79affef524468d1567b6c61997fbf24bced6f02351b84.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "30177d10e5454e4d99f3543601d099f3b426992ce95d254a4a966577b1c67d01", "generation_seconds_batch": 18.387009910074994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12076504528522491, "target_z": -0.4101562387482554, "ce": 6.205295085906982, "genuineness": 4.494794845581055, "identity": 0.7729766368865967, "hypothesis": "La route tourne à gauche après le pont continue jusqu'à la petite barrière et on boit. Je t'attendrai de l'autre côté.", "wer": 0.15, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "ed27b7dc8a0ae1e5e1f1e53cc67ac2c2d064bcc6a4f2408052255310ffedf6da", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "dc96ea1a2bc8a55a5b4f95d11bbbe33fcfe5f1f2e2f82ee53061b2d347008e21", "generation_seconds_batch": 25.174343492952175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6945065855979919, "target_z": 0.6562499930758495, "ce": 6.173524379730225, "genuineness": 3.8922953605651855, "identity": 0.6645338535308838, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ed27b7dc8a0ae1e5e1f1e53cc67ac2c2d064bcc6a4f2408052255310ffedf6da.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "ed4044afcfde9f7f4bc5bb22cc6eeabebb9bb994383190ba334cf9420eb3df94", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "65cfa5b1292556ee6a015b620564e8bc9947a4b77ad9edb72216db2615886fe7", "generation_seconds_batch": 17.00668077194132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8630058765411377, "target_z": 2.828125024234527, "ce": 6.09409761428833, "genuineness": 3.848362922668457, "identity": 0.44647082686424255, "hypothesis": "Ik 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_Teasing/ed4044afcfde9f7f4bc5bb22cc6eeabebb9bb994383190ba334cf9420eb3df94.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "ed4ff9f6571000804a7e7609eaf830407d68b7ca8a83f5f7a5c0e10d2d85cb16", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "01f02c709727e29decc703cb76a8177daeda62d44921ce5701300f515c0b2529", "generation_seconds_batch": 28.803856368991546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1617465764284134, "target_z": -0.3339843788948347, "ce": 6.332377910614014, "genuineness": 4.432034492492676, "identity": 0.6662405729293823, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ed4ff9f6571000804a7e7609eaf830407d68b7ca8a83f5f7a5c0e10d2d85cb16.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "ed55dd21fafc65a402becab5ac41f1f81a7cdbfe130b6f5148bfb37ac7474125", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "33a6df1b06ce4503d0e63cea2b79d467040081412e6e4125d45e7647c16288fe", "generation_seconds_batch": 17.451455220929347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9134446382522583, "target_z": 2.921874920372269, "ce": 6.1894097328186035, "genuineness": 4.143336772918701, "identity": 0.4363514184951782, "hypothesis": "Ik 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_Teasing/ed55dd21fafc65a402becab5ac41f1f81a7cdbfe130b6f5148bfb37ac7474125.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": "ee0d56acb1b7127f33e070dea65d1038d8564e83e85fb2a813998a26da362609", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2d92ffc811a8775a19553431ad1e28f518e938fd408d78ea4b28c5818fc461a0", "generation_seconds_batch": 16.098751422017813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9302575588226318, "target_z": 2.9531248857515164, "ce": 6.157639026641846, "genuineness": 4.055472373962402, "identity": 0.612515926361084, "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_Teasing/ee0d56acb1b7127f33e070dea65d1038d8564e83e85fb2a813998a26da362609.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": "ee2b019cb0be94d5deac124e31464d0e543aaf4164c0bfce259e3353c5ec11a3", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fc860b38b017137bf12a4ee9cf99fbd0207e814c0a3f2f0ef6b4aca1f96e160d", "generation_seconds_batch": 18.682233405997977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7032829523086548, "target_z": 2.5312500207724518, "ce": 6.356205940246582, "genuineness": 3.8671910762786865, "identity": 0.19573631882667542, "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_Teasing/ee2b019cb0be94d5deac124e31464d0e543aaf4164c0bfce259e3353c5ec11a3.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "ee30b80594e97c7f5b0b30bfd614af9be23f5201bf0f7cf3b7657fb74281d960", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6e29af702f67474b338f075b4ce3eb15a8ad2b9e356280edb3596c3ddb1c83ea", "generation_seconds_batch": 16.692012754967436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2749228477478027, "target_z": 3.5937499515309463, "ce": 6.173524379730225, "genuineness": 4.005263805389404, "identity": 0.2778991758823395, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ee30b80594e97c7f5b0b30bfd614af9be23f5201bf0f7cf3b7657fb74281d960.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": "ee597977d34a4661b925a0da239d238c2584a87affc5f6b033dd85e50edaf530", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bf58c7ba9caa426527b8481d9d339dbe6a83c27d860cff9db0d17a09562855e1", "generation_seconds_batch": 26.979391054948792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38241639733314514, "target_z": 0.07617185985342072, "ce": 6.141753673553467, "genuineness": 4.111956596374512, "identity": 0.4964122176170349, "hypothesis": "Ik schreef het nummer op de envelop, lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ee597977d34a4661b925a0da239d238c2584a87affc5f6b033dd85e50edaf530.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "ee92908cc7fa94794af361d909d3c944214c283c2a56e89c3fc1967642398a5d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "566ac3edad25d7dfa0a70a9d5529e01c449b20c55e360f61e3634e2b3633d7d3", "generation_seconds_batch": 24.081009836983867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7764697074890137, "target_z": 0.8085938235690994, "ce": 6.24500846862793, "genuineness": 4.118232727050781, "identity": 0.33124905824661255, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ee92908cc7fa94794af361d909d3c944214c283c2a56e89c3fc1967642398a5d.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "ef4cb163ebf200244319ced726270c2e10033ecd890cbace601954b12dfaaab1", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5778ee0439d5a7a7fa7b16401b2083c2a473faa05de90f8694e905ed9b1d8e68", "generation_seconds_batch": 18.0261860989267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.770534634590149, "target_z": 2.656249882289441, "ce": 6.006728172302246, "genuineness": 3.8797430992126465, "identity": 0.5345828533172607, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ef4cb163ebf200244319ced726270c2e10033ecd890cbace601954b12dfaaab1.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "ef6563d15fa955dde144769ca84870bf9a96f92e8614dd24f75fda67ba64708d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c84d24e70620ed105193b4230f4d95842b3c1bd89ae0af6f5508876fbada9ef7", "generation_seconds_batch": 24.330598721047863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.19469153881073, "target_z": 1.5859375155793387, "ce": 6.372091293334961, "genuineness": 3.747946262359619, "identity": 0.5143451690673828, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ef6563d15fa955dde144769ca84870bf9a96f92e8614dd24f75fda67ba64708d.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": "ef9a1a29659a4f9824ae454764467430aad50b816af31acf3657d95399b1456a", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eba3f116d4fc7c60583bee0d8f03297adc2b31fd2b49bf3cbf1486a0fb713fdc", "generation_seconds_batch": 19.28190789592918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7453153133392334, "target_z": 2.6093750450069786, "ce": 6.395919322967529, "genuineness": 4.137060642242432, "identity": 0.22666089236736298, "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_Teasing/ef9a1a29659a4f9824ae454764467430aad50b816af31acf3657d95399b1456a.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "f04165c0bd3a7239dac9af0f2301222cc5e32c95e5b4824191fd96546770e18c", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9e3c08b11a2c6dea37dfefaac6410911e9621bebbbd6684923186c513027310d", "generation_seconds_batch": 20.807573211030103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.745685338973999, "target_z": 4.468750311586774, "ce": 6.205295085906982, "genuineness": 4.193545341491699, "identity": 0.7334705591201782, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f04165c0bd3a7239dac9af0f2301222cc5e32c95e5b4824191fd96546770e18c.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": "f06ab4dfe80b2f5ba4978f3084b1ea59c5f21f920bbd90d87a388383052ee802", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6ed0055346fcb5ba26ed9e9030e2c9a84a792011c72621ffeced1e5375b0837b", "generation_seconds_batch": 23.769933174015023, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.367394208908081, "target_z": 3.7656253150488492, "ce": 6.324435234069824, "genuineness": 4.3127899169921875, "identity": 0.18777087330818176, "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_Teasing/f06ab4dfe80b2f5ba4978f3084b1ea59c5f21f920bbd90d87a388383052ee802.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "f07e9bf7fd551172f818e7435e6f1b1048ba35ea30145341ef521a9b88dbcb8b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a2be591a64a82888fb6afedc1da2a035770ebb4089c432f68a3b77b66c8f6d88", "generation_seconds_batch": 23.611698842025362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5519664287567139, "target_z": 2.2499998892135915, "ce": 6.268836498260498, "genuineness": 4.105680465698242, "identity": 0.49854576587677, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f07e9bf7fd551172f818e7435e6f1b1048ba35ea30145341ef521a9b88dbcb8b.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": "f091d1f05e135a2bf9bdf0692382e082ed74d0e58b7a4c1c48850e33605ece5c", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "309140c1795864367d44d820df23775bc04ed491a7773e93bf2aea46dfe43f30", "generation_seconds_batch": 17.160850384971127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9050382375717163, "target_z": 2.9062500484690537, "ce": 6.213237762451172, "genuineness": 3.9801597595214844, "identity": 0.6068869829177856, "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_Teasing/f091d1f05e135a2bf9bdf0692382e082ed74d0e58b7a4c1c48850e33605ece5c.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "f0a4a02ce6e72d378fd267eec54b3f86aea353b8d495eeac23b3f9dce221956b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "bb180efb9888e4ff4cbd4bb0b0d76a03943ee74a93e59fdda2a86c5a2836679b", "generation_seconds_batch": 25.814632244990207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7995874881744385, "target_z": 0.8515625536621666, "ce": 6.332377910614014, "genuineness": 4.105680465698242, "identity": 0.6503674983978271, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f0a4a02ce6e72d378fd267eec54b3f86aea353b8d495eeac23b3f9dce221956b.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "f0fd134c485ada2f517f66d31878dfab56d9bc7e5d80e2f4bd29858dd8488f27", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1f2cbca010c28cb16f670167292d0571e598f0d03459d4811fc2bd8d4236cf32", "generation_seconds_batch": 21.544205259997398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0770009756088257, "target_z": 1.3671875363517902, "ce": 6.117925643920898, "genuineness": 4.250029563903809, "identity": 0.5218544602394104, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f0fd134c485ada2f517f66d31878dfab56d9bc7e5d80e2f4bd29858dd8488f27.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": "f158072c9ff9c0e9d4f00fde8c455d8ae551e71998d276d2a0abcf1b7f4c43a5", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "174d9188f4aeb4f4632157a604cc148de81c2ca374995e2f165ac18a03b58b83", "generation_seconds_batch": 17.487501519033685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2030980587005615, "target_z": 1.6015626090553707, "ce": 6.427689552307129, "genuineness": 4.243753433227539, "identity": 0.5841798782348633, "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_Teasing/f158072c9ff9c0e9d4f00fde8c455d8ae551e71998d276d2a0abcf1b7f4c43a5.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "f19b9d636c0e8732d3b52becac8bca35e46959c13e670f10ea18f4a8393987c5", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "efd12408aab98423d6e9e245542d54b85f7aaaa9b78f502b2263187a297c0b9a", "generation_seconds_batch": 25.157836435944773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15228930115699768, "target_z": -0.35156249826896235, "ce": 6.165581703186035, "genuineness": 4.413206577301025, "identity": 0.538555920124054, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f19b9d636c0e8732d3b52becac8bca35e46959c13e670f10ea18f4a8393987c5.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "f1dbeaa6d55c7769be606e391d8c67c9b9fe02dec9b035e78cea36d39fa15b33", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bbfbd99a1d2b3445a09ebbcec3f740d0d6913bbcfab47783f599419d471b3ee7", "generation_seconds_batch": 25.11878526106011, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9635136127471924, "target_z": 1.1562499930758494, "ce": 5.903473377227783, "genuineness": 3.9550557136535645, "identity": 0.5031092166900635, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f1dbeaa6d55c7769be606e391d8c67c9b9fe02dec9b035e78cea36d39fa15b33.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "246e022995a0cc944f69ff422e5da182bf98ddf31cfcad94ff940e640ed53afb", "generation_seconds_batch": 18.267638348974288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11761261522769928, "target_z": -0.4160156211051653, "ce": 6.117925643920898, "genuineness": 4.570107460021973, "identity": 0.8011289238929749, "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_Teasing/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "f31ccc71e5eb0470e40610e879ba194ac727c7073bb19441a75be24ae2555db9", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "78c26db4979fd03bef1640daef18426d30e85fb6806227998e7d9f6da5d2d165", "generation_seconds_batch": 24.20458872197196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7890793681144714, "target_z": 0.8320312422103306, "ce": 6.213237762451172, "genuineness": 4.080576419830322, "identity": 0.2617793083190918, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f31ccc71e5eb0470e40610e879ba194ac727c7073bb19441a75be24ae2555db9.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "f326aa61b82a84739a0f863d20b28d6db323cb3dbd21fb3c16f0c4d204b77cbc", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "37404292557b27bc8409ae894918a38f30328359654a681e17b1f580f14f9ced", "generation_seconds_batch": 23.40803610603325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6696569919586182, "target_z": 2.4687498684411397, "ce": 5.982900142669678, "genuineness": 4.268857479095459, "identity": 0.5626205205917358, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f326aa61b82a84739a0f863d20b28d6db323cb3dbd21fb3c16f0c4d204b77cbc.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "f343bbd4cc16c2b042afb47b4cdab56932ec2bc82f193a3b37294c12b92a1669", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "903c96976b97de6f5e3568c53fcab19c63d41b6187d892a1560c98533d68aeab", "generation_seconds_batch": 25.20699528499972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.451088786125183, "target_z": 2.0624998753652903, "ce": 6.324435234069824, "genuineness": 4.507347106933594, "identity": 0.6956492066383362, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f343bbd4cc16c2b042afb47b4cdab56932ec2bc82f193a3b37294c12b92a1669.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": "f3443d0b0c472789e6ea3994d4adc5ffc302837a2f7ccff5464c6eedd0a7fa85", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0a543ca0f6224dcfc3b27a6fe8f1b2aa62b873f579f7605a8f2c7fa73d080852", "generation_seconds_batch": 25.22583017195575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1442526578903198, "target_z": 1.4921873978687796, "ce": 6.300607204437256, "genuineness": 4.394378662109375, "identity": 0.5953865051269531, "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_Teasing/f3443d0b0c472789e6ea3994d4adc5ffc302837a2f7ccff5464c6eedd0a7fa85.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": "f460619b1d32644e45d5d90b231be99476a6c69996f6454991d925c87803626e", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a9d274700e43fbc583afab25145b4f1fbea24bbcb11655915d431443bc00c0a1", "generation_seconds_batch": 15.291657591005787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1316430568695068, "target_z": 1.468750090013957, "ce": 6.205295085906982, "genuineness": 4.055472373962402, "identity": 0.5996731519699097, "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_Teasing/f460619b1d32644e45d5d90b231be99476a6c69996f6454991d925c87803626e.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": "f46fc215551173f2b2e39c36e773c5b6f1ff6bf8f657d3a1f0b83f2ac10ade71", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9ff65d7c776d9a980d652a4aff582a423b2e32682d7129e0fb9f2c0d94b6f71a", "generation_seconds_batch": 17.546025832067244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7369087934494019, "target_z": 2.5937499515309463, "ce": 6.141753673553467, "genuineness": 4.268857479095459, "identity": 0.5968577861785889, "hypothesis": "La roue tourne à gauche après le pont. Continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.05, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f46fc215551173f2b2e39c36e773c5b6f1ff6bf8f657d3a1f0b83f2ac10ade71.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "f4849e609929338e0b8710c1161c0f1d21360a994209bfb54bed16feb1022324", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "755d62a1b2371efed16ced4e9cd3ffc979712831d873ce21a0079ff24993c587", "generation_seconds_batch": 23.9024544400163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4679017066955566, "target_z": 2.093749840744538, "ce": 5.831989288330078, "genuineness": 3.8420867919921875, "identity": 0.5453945994377136, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f4849e609929338e0b8710c1161c0f1d21360a994209bfb54bed16feb1022324.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "f4e233571bbb150d7332abf5d874fa78ab33a7f3f84d4d75d9bcadc526423ca1", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b163e3de22d01a1f044436b10639cd38601c731982d47650de9df1cd4a6e5769", "generation_seconds_batch": 26.33212081901729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1320128440856934, "target_z": 3.3281249134481183, "ce": 6.09409761428833, "genuineness": 3.4969046115875244, "identity": 0.25629091262817383, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f4e233571bbb150d7332abf5d874fa78ab33a7f3f84d4d75d9bcadc526423ca1.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "f5241219d5851792fee5bc1d90ff2ef7da8b44fb007cf2b130939a1b8c8b7d40", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f4e7c55a0f2526d2786df4d2393c97b25ce3d341b870ab1fb6f78222767bdf36", "generation_seconds_batch": 22.69566733308602, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.047948122024536, "target_z": 3.1718748649790647, "ce": 6.181467056274414, "genuineness": 3.7165660858154297, "identity": 0.3378431797027588, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f5241219d5851792fee5bc1d90ff2ef7da8b44fb007cf2b130939a1b8c8b7d40.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": "f5362e0939abe034e1e24946e91be61b3fad2e1eee2c78f4b7ddcffe3719f1d6", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "45215195f3ec3f01e8d03d1370b87d57b1ed08b488e1add5740041e5c9de065d", "generation_seconds_batch": 25.478480313904583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.039541721343994, "target_z": 3.1562499930758494, "ce": 6.316492557525635, "genuineness": 4.124508857727051, "identity": 0.6723562479019165, "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_Teasing/f5362e0939abe034e1e24946e91be61b3fad2e1eee2c78f4b7ddcffe3719f1d6.mp3" }, { "id": "emo_Teasing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-0", "key": "f545cc03e26eb22fe441369468b8ea00202022cb2081338dd256ab7b7256000e", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "dc0e758259d639f4ce86aefeda25302016d32cdc82bdca2124d3665708364a7d", "generation_seconds_batch": 25.75701088400092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24843829870224, "target_z": -0.17285155795602622, "ce": 6.221180438995361, "genuineness": 4.281409740447998, "identity": 0.7061110734939575, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f545cc03e26eb22fe441369468b8ea00202022cb2081338dd256ab7b7256000e.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "f565d58b98e0dc3a85c0562e22499f4979ca117f1b950d9ae5aa0f9ebde88aef", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "6d7d3c1a2a3ca44a5ff0150e8f198531a20e2402b3942608e2ad65846cd43fde", "generation_seconds_batch": 25.345221993979067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.014322280883789, "target_z": 3.10937493422057, "ce": 6.1894097328186035, "genuineness": 4.055472373962402, "identity": 0.6057124137878418, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "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_Teasing/f565d58b98e0dc3a85c0562e22499f4979ca117f1b950d9ae5aa0f9ebde88aef.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": "f56ad79ed22f1dd43396cb20dbd689588ac27de993618c7dd3dfaf699ac6b024", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ba8185b4f23ae82187b552160168422cfcb5db8cb27614ac075aeb32c155cef3", "generation_seconds_batch": 23.30688981001731, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5351535081863403, "target_z": 2.218749923834344, "ce": 6.324435234069824, "genuineness": 3.8420867919921875, "identity": 0.48188260197639465, "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_Teasing/f56ad79ed22f1dd43396cb20dbd689588ac27de993618c7dd3dfaf699ac6b024.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "f5be33abd25b4485f06c29f40f646037c1c4e17b0fe422e43181fffede9b6faf", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "208029eb1aad08e3506cf5aa7de317e76a27c73c317feb1016cfd5a87d3cb980", "generation_seconds_batch": 23.070804376038723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9719201326370239, "target_z": 1.1718750865518817, "ce": 6.4515180587768555, "genuineness": 4.017816066741943, "identity": 0.6097283363342285, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f5be33abd25b4485f06c29f40f646037c1c4e17b0fe422e43181fffede9b6faf.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "f5dc95db863154b3247eed5d0f9d90f620ca8ba0d63f50502bf94df35ad529e9", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "6db748dfa11f57d24acb94f59cfa2ab305143b7208fbd2807223c4ac28f08e6d", "generation_seconds_batch": 25.581573706003837, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.064761161804199, "target_z": 3.203125051931129, "ce": 6.133810997009277, "genuineness": 4.281409740447998, "identity": 0.6057981252670288, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f5dc95db863154b3247eed5d0f9d90f620ca8ba0d63f50502bf94df35ad529e9.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": "f74928d25e6f73f1e4976984ab88daf5cb4595632291ed4ea928dcb78e5166f9", "bucket": "emo_Teasing", "phase": "heldout", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "27c21422c1feff881ec280fd029f60f54e2ad71418376221fbe5ffd77979bc88", "generation_seconds_batch": 17.546025832067244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6528440713882446, "target_z": 2.4374999030618927, "ce": 6.125868320465088, "genuineness": 4.300237655639648, "identity": 0.7317615747451782, "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_Teasing/f74928d25e6f73f1e4976984ab88daf5cb4595632291ed4ea928dcb78e5166f9.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "75b7112dd01f45873ace2dbe5eeb70ca6a9e73d92a14a074e7ac564cd204dd83", "generation_seconds_batch": 17.07977716298774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11446018517017365, "target_z": -0.42187500346207524, "ce": 6.09409761428833, "genuineness": 4.419482707977295, "identity": 0.6428447365760803, "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_Teasing/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "f83b91c9626dc3340d3987e5077362d61b39be7449f0828463e38f7daaaae169", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a449a94cacf59e6dc09bf11dec753fe0e384f6bb2beaf3dfea5f26a67367651b", "generation_seconds_batch": 24.935827763052657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6528440713882446, "target_z": 2.4374999030618927, "ce": 6.24500846862793, "genuineness": 3.873466968536377, "identity": 0.3618418574333191, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f83b91c9626dc3340d3987e5077362d61b39be7449f0828463e38f7daaaae169.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_Teasing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": "bd898ba3c76bd83ff26f2bfd02c8ada672ee7a683bff5e95656f59f11ce2eb49", "generation_seconds_batch": 19.706193636055104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10605370998382568, "target_z": -0.43750001384830106, "ce": 6.395919322967529, "genuineness": 4.545003414154053, "identity": 0.626570463180542, "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_Teasing/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "f89a8e9f932db891ca800b0cbe599247554900f4e86820da526b27117278aefa", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a529d1181c90091b9946796b9c58188cb67441908a0af7d647ee63de24f4a755", "generation_seconds_batch": 16.603100317995995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3754305839538574, "target_z": 1.921874920372269, "ce": 6.23706579208374, "genuineness": 4.293961524963379, "identity": 0.7838382124900818, "hypothesis": "J'ai trouvé la 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_Teasing/f89a8e9f932db891ca800b0cbe599247554900f4e86820da526b27117278aefa.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "f8ebf6711e778d2a48eb46435792e473aafc1ec3780bddd5d1d95e6017700466", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7c87c9182b0d3fef2803f77bb176a68896dbc71354f6239e42b0cfc73f7e6f0c", "generation_seconds_batch": 25.35419981100131, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5267471075057983, "target_z": 2.203125051931129, "ce": 6.165581703186035, "genuineness": 4.111956596374512, "identity": 0.6056555509567261, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f8ebf6711e778d2a48eb46435792e473aafc1ec3780bddd5d1d95e6017700466.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "f8f5e3b96467a16ece44045c37207a5327473d0346bd91792dc2ece7e94cb919", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "097713d26e09c46476011eeb52607155abbc2b6ec423d915cffe97a185a9c5bd", "generation_seconds_batch": 23.158856668975204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.383837103843689, "target_z": 1.937500013848301, "ce": 6.340320587158203, "genuineness": 3.9676074981689453, "identity": 0.31183621287345886, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f8f5e3b96467a16ece44045c37207a5327473d0346bd91792dc2ece7e94cb919.mp3" }, { "id": "emo_Teasing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-1", "key": "f999337c592b5dacf5f7a27557e42ef51db03a41a7d3b18bc52221d3eb5b8c21", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "916adbfcaea13741b7924c77c4e145ce34d0b2f4067a06f53b7018f9c26097ad", "generation_seconds_batch": 26.428511556005105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5351535081863403, "target_z": 2.218749923834344, "ce": 6.221180438995361, "genuineness": 4.356721878051758, "identity": 0.54338139295578, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f999337c592b5dacf5f7a27557e42ef51db03a41a7d3b18bc52221d3eb5b8c21.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "f9a03654759b71e8f3548def2e5352795a746e4445f1a866b7a783513e0df527", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "202c877bfa097ce053b4688c482d4e8890b8553ff5bf4190814d5f98e5de04b8", "generation_seconds_batch": 23.909309884067625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6111817359924316, "target_z": 4.218750145407161, "ce": 6.086154937744141, "genuineness": 3.8797430992126465, "identity": 0.411822110414505, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bist.", "wer": 0.05263157894736842, "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_Teasing/f9a03654759b71e8f3548def2e5352795a746e4445f1a866b7a783513e0df527.mp3" }, { "id": "emo_Teasing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-0", "key": "f9b63f75f8ce5e8728dabecf29a9739aa8cfbf6b57a08ba05ecf27941f0102f7", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] The door is still open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] I put your coat on the chair.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9d24b18254ca660d977318ea8593e906e5b3e309645af5159fd72e0cc84c5f32", "generation_seconds_batch": 24.3086674970109, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7659615874290466, "target_z": 0.7890625121172634, "ce": 6.3641486167907715, "genuineness": 3.9676074981689453, "identity": 0.2272961437702179, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f9b63f75f8ce5e8728dabecf29a9739aa8cfbf6b57a08ba05ecf27941f0102f7.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "f9f6b31be41e81a2d7111f3a2479cd43239ccabf4c0a234e117fef7cfb4553e9", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "36620e87a00ca9dc7a359b5748e3b2b0239e60d61d466b47c8612262f1a3fd0a", "generation_seconds_batch": 21.91457379097119, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1908581256866455, "target_z": 3.4374999030618927, "ce": 5.760505676269531, "genuineness": 3.6914620399475098, "identity": 0.5756769180297852, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/f9f6b31be41e81a2d7111f3a2479cd43239ccabf4c0a234e117fef7cfb4553e9.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "fa2a35a103db42143d6b647ff5e7fb8a6d050bac491893ea73d3feddbf71a84b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f5bbe9b2e639e9788ddb7327bab62bbeb62a7838dc0d4cd7310a4cc0fa722991", "generation_seconds_batch": 26.03753468603827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9256844520568848, "target_z": 1.0859374047929302, "ce": 6.117925643920898, "genuineness": 3.6412534713745117, "identity": 0.36957496404647827, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/fa2a35a103db42143d6b647ff5e7fb8a6d050bac491893ea73d3feddbf71a84b.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "fa7a27bcfb361f495dbb7d57ee805baa96b6ccee2ac54a1bd10a477788482a09", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1304016debd846d3b538e31fd6da6578263235f1b7572d8861709f3916bfb0d4", "generation_seconds_batch": 17.579845652915537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1064236164093018, "target_z": 1.4218750311586774, "ce": 6.252951145172119, "genuineness": 3.7793264389038086, "identity": 0.403229683637619, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. Podemos mirar.", "wer": 0.35294117647058826, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/fa7a27bcfb361f495dbb7d57ee805baa96b6ccee2ac54a1bd10a477788482a09.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "fabe32120fd0c7aba0ad63cb11a1afaf975638eb4ad7ad7bfe09f78bdf07543d", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "cd8adca51856f29591546c4a6bd94b29535ba1c98c6b3858daf61275d785fdf0", "generation_seconds_batch": 25.733510710066184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0899806022644043, "target_z": 3.2500001107864085, "ce": 6.213237762451172, "genuineness": 4.18726921081543, "identity": 0.6145807504653931, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/fabe32120fd0c7aba0ad63cb11a1afaf975638eb4ad7ad7bfe09f78bdf07543d.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "fb1dc0efe0320cc46bd71255053a6cee46648cf858c1683d755b75646a878fd4", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d7bdcd4338152dbaf325c56cb588c723ce2fb5a2babae5ee60d4c220fb5abf20", "generation_seconds_batch": 23.92317056306638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2619433403015137, "target_z": 1.710937598669145, "ce": 6.09409761428833, "genuineness": 3.9927117824554443, "identity": 0.4070051312446594, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/fb1dc0efe0320cc46bd71255053a6cee46648cf858c1683d755b75646a878fd4.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "fb4f7dc0c7252ffbc9371ba82d8fc9d9614f6d86d0788fd75bffa626e9213d45", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d4589859b453c07453066b0a592d1809474f9f569a1bb20f30d9f0097eaa4c3c", "generation_seconds_batch": 23.79760507598985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6650839447975159, "target_z": 0.6015624982689624, "ce": 6.229123115539551, "genuineness": 4.268857479095459, "identity": 0.6264145374298096, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/fb4f7dc0c7252ffbc9371ba82d8fc9d9614f6d86d0788fd75bffa626e9213d45.mp3" }, { "id": "emo_Teasing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-fr-1", "key": "fb95e082ae5c902652aa60bfdfceec34c032c7bfdc7c0169ea7059c926326278", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4da55b0e2e7b6b7e48ba9c5188c47cc41d987212a994a318b6620de10a10f3aa", "generation_seconds_batch": 26.008283275994472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21691402792930603, "target_z": -0.23144532613192134, "ce": 6.229123115539551, "genuineness": 4.231201171875, "identity": 0.6625455617904663, "hypothesis": "J'ai trouvé la 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_Teasing/fb95e082ae5c902652aa60bfdfceec34c032c7bfdc7c0169ea7059c926326278.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "fc149153299944b15405e3d21b505b467ba2031998fb30ed10ebe4770bfc2805", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "be0ab2a2f6c0cbe3b6a641a424126ea9c51de62d5fc89b01b0d588c81d5f2d9c", "generation_seconds_batch": 24.63613225298468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2661465406417847, "target_z": 1.7187500346207527, "ce": 6.117925643920898, "genuineness": 4.13078498840332, "identity": 0.7524700164794922, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/fc149153299944b15405e3d21b505b467ba2031998fb30ed10ebe4770bfc2805.mp3" }, { "id": "emo_Teasing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-1", "key": "fc32be7fed09ffa347600eaa0f2025f96133f736a892b1cf714547b965df25a8", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "331e0b550a918f8c5cf86cc8fbdcb520e3c7708c912495aa543f861230d32dab", "generation_seconds_batch": 23.814453003928065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9593104124069214, "target_z": 1.1484375571242418, "ce": 6.284721851348877, "genuineness": 3.7165660858154297, "identity": 0.6618185043334961, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/fc32be7fed09ffa347600eaa0f2025f96133f736a892b1cf714547b965df25a8.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "fe2e716671e03f652d31283a3dea914da7621a285201debee6a5d6e02a167bbe", "bucket": "emo_Teasing", "phase": "wording", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "051119e5bd8147a83eabc10eb94b40b9a918d4a05ed2c34dddba4a4825400832", "generation_seconds_batch": 16.711742885992862, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1236064434051514, "target_z": 3.312500041544903, "ce": 6.149696350097656, "genuineness": 4.15588903427124, "identity": 0.26229697465896606, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/fe2e716671e03f652d31283a3dea914da7621a285201debee6a5d6e02a167bbe.mp3" }, { "id": "emo_Teasing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-0", "key": "fe6ec192c5aee2e6fa98b0da5ffa307fb68776876eeff7bb1a4dbb82eede276b", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9cd7a3bbbf15973901a3c7c7fa029fd63ff7ad60b3bb989eb9242a5b324bd573", "generation_seconds_batch": 23.60380029294174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7407422065734863, "target_z": 0.7421875640483924, "ce": 5.855817794799805, "genuineness": 3.848362922668457, "identity": 0.4744148254394531, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/fe6ec192c5aee2e6fa98b0da5ffa307fb68776876eeff7bb1a4dbb82eede276b.mp3" }, { "id": "emo_Teasing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-nl-0", "key": "fee4526152652606b79aa7201760d0339c3df03585e06712f702a8184aa7d2ad", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] De deur staat nog open.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "286438e8c5e3c36d628b1a85c8509be606fdbc587cd5b98d4f4a2997c05d11bf", "generation_seconds_batch": 22.354152506915852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6612505912780762, "target_z": 2.453124996537925, "ce": 6.022613525390625, "genuineness": 4.143336772918701, "identity": 0.6279646754264832, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/fee4526152652606b79aa7201760d0339c3df03585e06712f702a8184aa7d2ad.mp3" }, { "id": "emo_Teasing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-es-1", "key": "ff9088e1df516191e71172d4b0798c7a0035a4aed28573ecb507ae495a996c24", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] He encontrado la cajita.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b68e5e1e83b21160e01b3c109faca7d04a47b18f2c97cfaeb6c84da166695798", "generation_seconds_batch": 14.934474849957041, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2786490321159363, "target_z": -0.11669924525651375, "ce": 6.24500846862793, "genuineness": 4.243753433227539, "identity": 0.5667471885681152, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ff9088e1df516191e71172d4b0798c7a0035a4aed28573ecb507ae495a996c24.mp3" }, { "id": "emo_Teasing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-en-1", "key": "ff987e9b1a29ddc108c66408dbf04ebf3dae94f08b01e00f4975de780ddffed3", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] I found the little box.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] It was beside the old window.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e3fc840314fe30b450373145d850e3e3a87900e911c76d948a30bcf9e8881f23", "generation_seconds_batch": 22.367336611961946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.636031150817871, "target_z": 2.406249937682645, "ce": 6.38003396987915, "genuineness": 4.243753433227539, "identity": 0.30083417892456055, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ff987e9b1a29ddc108c66408dbf04ebf3dae94f08b01e00f4975de780ddffed3.mp3" }, { "id": "emo_Teasing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Teasing-de-0", "key": "ffea8a7ab739174d40b82ceb9fdf7653e1187e7c4161ac34b657b6418dce247f", "bucket": "emo_Teasing", "phase": "grid", "candidate": "manual-c46a333eb8dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Begin with an overly sweet, almost saccharine inflection, immediately setting up the ironic contrast.) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce subtle, rhythmic vocal emphasis on the unstressed syllables to create a buoyant, teasing cadence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with a clear, bright resonance, ensuring the underlying flirtatious challenge is perfectly audible.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f12017f164a7031c72717cb97714a640f50104c78fdece26ca989a37e7122862", "generation_seconds_batch": 18.127522705006413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6780635118484497, "target_z": 2.484374961917172, "ce": 6.284721851348877, "genuineness": 4.218649387359619, "identity": 0.5003897547721863, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Teasing/ffea8a7ab739174d40b82ceb9fdf7653e1187e7c4161ac34b657b6418dce247f.mp3" }, { "key": "original-emo_Teasing-de-0-seed1701-scale0.0", "bucket": "emo_Teasing", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "efec74ea279146997c8536c3bbf2d432d08f69f6538c39f5a7f54424f4ccd3e2", "task_id": "emo_Teasing-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.3826791048049927, "target_z": 0.07666015094869726, "ce": 6.165581703186035, "genuineness": 4.369274139404297, "identity": 0.5558395385742188, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/de/06852331b0a9e82f2fe0e0ee.mp3" }, { "key": "original-emo_Teasing-de-0-seed1701-scale0.5", "bucket": "emo_Teasing", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "e05097f02eae07399477653f36539121931168469ea0af5a303c3f0000f53479", "task_id": "emo_Teasing-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.3606121242046356, "target_z": 0.035644529843531926, "ce": 6.23706579208374, "genuineness": 4.406930446624756, "identity": 0.38411033153533936, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/de/f8d1376724827b5e8fdcddc9.mp3" }, { "key": "original-emo_Teasing-de-0-seed1701-scale0.75", "bucket": "emo_Teasing", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "63b9f0815fedff2cb0795f1bd388410dc3c286cb97b03248bdc90911976f451c", "task_id": "emo_Teasing-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.26892906427383423, "target_z": -0.13476562802931585, "ce": 6.09409761428833, "genuineness": 4.457139015197754, "identity": 0.5763466358184814, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/de/7e96661945e2f6cf603b5e6c.mp3" }, { "key": "original-emo_Teasing-de-0-seed1701-scale1.0", "bucket": "emo_Teasing", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "a92e8b24a8285406c1964c43c50df97005c39b2e5f26b0179285f9af8fb441a5", "task_id": "emo_Teasing-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.1480860710144043, "target_z": -0.35937498961377423, "ce": 6.260893821716309, "genuineness": 4.582659721374512, "identity": 0.5590536594390869, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/de/550cb442955a02ab88897d02.mp3" }, { "key": "original-emo_Teasing-de-0-seed1702-scale0.0", "bucket": "emo_Teasing", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "419afc988712b4881d766af3e3a004a7d0d6c63d406896427ff2a1d1affa7e8f", "task_id": "emo_Teasing-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.812197208404541, "target_z": 0.8750000830898064, "ce": 6.332377910614014, "genuineness": 4.65797233581543, "identity": 0.6069127917289734, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/de/f8a31f2085f22f36eaaf987e.mp3" }, { "key": "original-emo_Teasing-de-0-seed1702-scale0.5", "bucket": "emo_Teasing", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "deb47f015e73d1d78fb40de66c7ea4a451e81850fd0de1bcf4d98a2ec1de29d5", "task_id": "emo_Teasing-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.127069890499115, "target_z": -0.39843750173103765, "ce": 6.229123115539551, "genuineness": 4.425758361816406, "identity": 0.7237501740455627, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/de/0e501255396f446b3ca14d35.mp3" }, { "key": "original-emo_Teasing-de-0-seed1702-scale0.75", "bucket": "emo_Teasing", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "3010c9b916b7d8bd0c2e349e919aab1db11bb8ce634c3bb86b77b38141778015", "task_id": "emo_Teasing-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.10500290989875793, "target_z": -0.43945312283620297, "ce": 6.340320587158203, "genuineness": 4.7081804275512695, "identity": 0.7170528173446655, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/de/e66fff94011aac338892cb52.mp3" }, { "key": "original-emo_Teasing-de-0-seed1702-scale1.0", "bucket": "emo_Teasing", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "0e5e7eee78cb2612e7e6bc19d1bbf0bf27fd2f951a48a720d32416f2e12458c2", "task_id": "emo_Teasing-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.27497121691703796, "target_z": -0.12353515441077252, "ce": 6.252951145172119, "genuineness": 4.457139015197754, "identity": 0.5855762958526611, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/de/1135ee6f58189f446d7b7771.mp3" }, { "key": "original-emo_Teasing-de-1-seed1701-scale0.0", "bucket": "emo_Teasing", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "200aeba6d549c5f649f2875d21e59153bde4965289174a7def32744edfa31c4a", "task_id": "emo_Teasing-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.14073041081428528, "target_z": -0.37304686331549597, "ce": 6.268836498260498, "genuineness": 3.9173994064331055, "identity": 0.6995257139205933, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/de/02d4feb505ac3b82e6d1ee26.mp3" }, { "key": "original-emo_Teasing-de-1-seed1701-scale0.5", "bucket": "emo_Teasing", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "ccf5bffde3e66218c71bca4dd03cef20a2453c8b32c24d9f899b858730736ed8", "task_id": "emo_Teasing-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.17540709674358368, "target_z": -0.308593740479293, "ce": 6.38003396987915, "genuineness": 4.532451152801514, "identity": 0.5662997364997864, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/de/44ecbd0996ccf893655d02ca.mp3" }, { "key": "original-emo_Teasing-de-1-seed1701-scale0.75", "bucket": "emo_Teasing", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "8d00104b26b0e1c29b40148a114d4105ec8dc4b81f16c53520025b559d84d787", "task_id": "emo_Teasing-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.19011841714382172, "target_z": -0.28124999307584947, "ce": 6.24500846862793, "genuineness": 4.268857479095459, "identity": 0.5399528741836548, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/de/bcc16228e5d3d55a76b53615.mp3" }, { "key": "original-emo_Teasing-de-1-seed1701-scale1.0", "bucket": "emo_Teasing", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "3f65ce6798e9fd80fe30d593a5dfbcbb781ca1d069814500cd4af9b3dde7a39e", "task_id": "emo_Teasing-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.25684475898742676, "target_z": -0.15722657526640255, "ce": 6.403861999511719, "genuineness": 4.394378662109375, "identity": 0.5455867052078247, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/de/bc84128416d3d708b0e6fb58.mp3" }, { "key": "original-emo_Teasing-de-1-seed1702-scale0.0", "bucket": "emo_Teasing", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "0ef4be28b948040a005ceda694bb4aea5ef1dce54d03a799cf30d802f1fd1aec", "task_id": "emo_Teasing-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.13967959582805634, "target_z": -0.375, "ce": 6.38797664642334, "genuineness": 3.8922953605651855, "identity": 0.3232930600643158, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/de/f57cfe687c46bc7d0ecccdac.mp3" }, { "key": "original-emo_Teasing-de-1-seed1702-scale0.5", "bucket": "emo_Teasing", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "be772a5856fae403fdfe8e77a0281cc366aa794c31f0aff8802e85c6c55d1488", "task_id": "emo_Teasing-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.20272812247276306, "target_z": -0.2578124913448118, "ce": 6.38797664642334, "genuineness": 4.482243061065674, "identity": 0.4814472198486328, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/de/a852d4f19d0f13d83d2917d6.mp3" }, { "key": "original-emo_Teasing-de-1-seed1702-scale0.75", "bucket": "emo_Teasing", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "e51cd2b1edb8dd44f3d3d5b130c03b3df237a70c34ed4138c85a82dfb2d7d45e", "task_id": "emo_Teasing-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.2058805376291275, "target_z": -0.25195313668450403, "ce": 6.324435234069824, "genuineness": 4.319066047668457, "identity": 0.6070418357849121, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/de/fde5eca364e2eaac226ee802.mp3" }, { "key": "original-emo_Teasing-de-1-seed1702-scale1.0", "bucket": "emo_Teasing", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "79716872a45c866acdc43ffb343fa68e120acc754dff7e0e6c9e2a6883dfbc20", "task_id": "emo_Teasing-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.19957569241523743, "target_z": -0.2636718737017218, "ce": 6.395919322967529, "genuineness": 4.337893962860107, "identity": 0.46422627568244934, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/de/42e6f2a637cf69089f12a24a.mp3" }, { "key": "original-emo_Teasing-en-0-seed1701-scale0.0", "bucket": "emo_Teasing", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "3f9d7897a05bd1067a6b18aab3e5a577f20e69e352dfdf89507a03e3b2a8c296", "task_id": "emo_Teasing-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.23530319333076477, "target_z": -0.1972656141810148, "ce": 6.308549880981445, "genuineness": 3.9927117824554443, "identity": 0.38291847705841064, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/en/fa99835ae8e2373b19e85265.mp3" }, { "key": "original-emo_Teasing-en-0-seed1701-scale0.5", "bucket": "emo_Teasing", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.5, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "07b24a92fed448ae3a47e3f1f5cc3da818e8efe12b2ff0e0adbce55b0f66a09b", "task_id": "emo_Teasing-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.21113458275794983, "target_z": -0.24218750865518815, "ce": 6.300607204437256, "genuineness": 4.080576419830322, "identity": 0.2910805344581604, "hypothesis": "The 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_Teasing/en/b28bc18369a2e137adb1f25f.mp3" }, { "key": "original-emo_Teasing-en-0-seed1701-scale0.75", "bucket": "emo_Teasing", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "761be8c11c1b094653e64354e46410e4133e383ee6d0dbfb94a326f9829aac07", "task_id": "emo_Teasing-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.16384819149971008, "target_z": -0.33007813322242874, "ce": 6.268836498260498, "genuineness": 4.030367851257324, "identity": 0.13638731837272644, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/en/9c2108b941ede37f3966128d.mp3" }, { "key": "original-emo_Teasing-en-0-seed1701-scale1.0", "bucket": "emo_Teasing", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "76f8d637cb068f8a7ba1a9b5dfc55acdade76d0dea65a63725551b0d92fedd5c", "task_id": "emo_Teasing-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.39476341009140015, "target_z": 0.09912109818578393, "ce": 6.09409761428833, "genuineness": 4.18099308013916, "identity": 0.4667607247829437, "hypothesis": "The 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_Teasing/en/19f08c896b5a82217cf72b0e.mp3" }, { "key": "original-emo_Teasing-en-0-seed1702-scale0.0", "bucket": "emo_Teasing", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "1a3eda8f41a578b9e110d467b2a8a139e5c170c895aa9a9bc48b8964eb65842f", "task_id": "emo_Teasing-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.1480860710144043, "target_z": -0.35937498961377423, "ce": 6.062326908111572, "genuineness": 3.9927117824554443, "identity": 0.23725885152816772, "hypothesis": "The 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_Teasing/en/50b23b7cb8ccf2e3cd016588.mp3" }, { "key": "original-emo_Teasing-en-0-seed1702-scale0.5", "bucket": "emo_Teasing", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "07098a110067d03c1562ddf4aa526cf9a8e58561200b8dc2fb74c52632d02d3c", "task_id": "emo_Teasing-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.26052260398864746, "target_z": -0.15039061071893953, "ce": 6.109982967376709, "genuineness": 3.7793264389038086, "identity": 0.26042813062667847, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/en/20d57bf9ba3d6f8e05d9c987.mp3" }, { "key": "original-emo_Teasing-en-0-seed1702-scale0.75", "bucket": "emo_Teasing", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "063c8090465397602dcf1c8e20014d5fb99ed65f64f2543f129e084a5cf4936b", "task_id": "emo_Teasing-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.3459008038043976, "target_z": 0.008300782440088372, "ce": 6.324435234069824, "genuineness": 4.093128204345703, "identity": 0.22807735204696655, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/en/cc32dd13ad6457aaeddfc8ce.mp3" }, { "key": "original-emo_Teasing-en-0-seed1702-scale1.0", "bucket": "emo_Teasing", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "8197fb01f66e27b495ab65fa9f0c35bfdcdc56ad3d1f227cc2900e3639222481", "task_id": "emo_Teasing-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.09134238958358765, "target_z": -0.4648437612517446, "ce": 6.268836498260498, "genuineness": 3.7667744159698486, "identity": 0.24813063442707062, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/en/5a74dc2e2423daa236ea3a81.mp3" }, { "key": "original-emo_Teasing-en-1-seed1701-scale0.0", "bucket": "emo_Teasing", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "97e829b880c386e61590926be570e460e621bc015bf211ddac72f1c0cee5c9d8", "task_id": "emo_Teasing-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19537246227264404, "target_z": -0.2714843650465336, "ce": 6.348263263702393, "genuineness": 4.507347106933594, "identity": 0.3220953345298767, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/en/a1a16ca4f6cc9e343dbc9b8f.mp3" }, { "key": "original-emo_Teasing-en-1-seed1701-scale0.5", "bucket": "emo_Teasing", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "6dc43b028452ccbe6310df0d13634f1a536f527249ad9d6f374fe957e9e22893", "task_id": "emo_Teasing-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18591517210006714, "target_z": -0.2890625121172634, "ce": 6.3641486167907715, "genuineness": 4.482243061065674, "identity": 0.41647106409072876, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/en/ca72a8df05881ea7bc7adeb9.mp3" }, { "key": "original-emo_Teasing-en-1-seed1701-scale0.75", "bucket": "emo_Teasing", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "6e1b73fb7a7a84e31b67dd7234af72da48c3d80e36ce12a48fe0bab34c248c87", "task_id": "emo_Teasing-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1365271657705307, "target_z": -0.3808593823569099, "ce": 6.3641486167907715, "genuineness": 4.344170093536377, "identity": 0.4119141697883606, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/en/017fcb67c027a0eb3645d468.mp3" }, { "key": "original-emo_Teasing-en-1-seed1701-scale1.0", "bucket": "emo_Teasing", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "e67501a6c9add2cbe5868ab8027bb55e634bb379a21072c246b8d46521637226", "task_id": "emo_Teasing-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15859414637088776, "target_z": -0.3398437612517446, "ce": 6.4515180587768555, "genuineness": 4.444586753845215, "identity": 0.47158724069595337, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/en/f7d1bc40abc392273da7c6d1.mp3" }, { "key": "original-emo_Teasing-en-1-seed1702-scale0.0", "bucket": "emo_Teasing", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "bcc8c1459c24d3d8a4776b37414773e47675e94accdfae32b37f2f31c5687024", "task_id": "emo_Teasing-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.423397958278656, "target_z": 0.15234377510004565, "ce": 6.157639026641846, "genuineness": 4.2249250411987305, "identity": 0.35433417558670044, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/en/8805947fbde5b569cd94b3dc.mp3" }, { "key": "original-emo_Teasing-en-1-seed1702-scale0.5", "bucket": "emo_Teasing", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "89f6526a55ece090b511821309ce094871de9f2489644e245a0e9b15120b149f", "task_id": "emo_Teasing-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17015305161476135, "target_z": -0.31835936850860885, "ce": 6.316492557525635, "genuineness": 4.3881025314331055, "identity": 0.4204549789428711, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/en/0ff961ef32e408175534d3f8.mp3" }, { "key": "original-emo_Teasing-en-1-seed1702-scale0.75", "bucket": "emo_Teasing", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "6e41d041ad88dfd6f20dbfe38d0291cd7f57abc706cbf33a61ad418bc57c5bb2", "task_id": "emo_Teasing-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17015305161476135, "target_z": -0.31835936850860885, "ce": 6.356205940246582, "genuineness": 4.413206577301025, "identity": 0.4421054720878601, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/en/8a1d143c65af6777336d7a57.mp3" }, { "key": "original-emo_Teasing-en-1-seed1702-scale1.0", "bucket": "emo_Teasing", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "3ca37cbc747570531b8fea081b470d84f6b37e06b497087da127f69af20a9e5f", "task_id": "emo_Teasing-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18171194195747375, "target_z": -0.29687500346207524, "ce": 6.38003396987915, "genuineness": 4.419482707977295, "identity": 0.38783159852027893, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/en/331f05400c8287a6b9524fbf.mp3" }, { "key": "original-emo_Teasing-es-0-seed1701-scale0.0", "bucket": "emo_Teasing", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "3efa33fa0474a5ac13df4c4ecf73eb8bc49ff4ca0ecc976d08c9359af3d3d9a3", "task_id": "emo_Teasing-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.0556148886680603, "target_z": -0.5312500207724515, "ce": 6.125868320465088, "genuineness": 4.319066047668457, "identity": 0.5700371265411377, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/es/f5a802d031c72debc8b754d5.mp3" }, { "key": "original-emo_Teasing-es-0-seed1701-scale0.5", "bucket": "emo_Teasing", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "187ab5bc102849337e453064b4958374b460c603b2ba2b16300ba604ac5c4706", "task_id": "emo_Teasing-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.4832940399646759, "target_z": 0.2636718737017218, "ce": 6.117925643920898, "genuineness": 4.331617832183838, "identity": 0.5174990892410278, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/es/c18b1a2f098009564c94a98b.mp3" }, { "key": "original-emo_Teasing-es-0-seed1701-scale0.75", "bucket": "emo_Teasing", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "1dbc000affc9d500ae7250ca9cf1dc727567b11800c531c5220b63f87a49e7c5", "task_id": "emo_Teasing-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.09344401955604553, "target_z": -0.4609374878827366, "ce": 5.784333229064941, "genuineness": 3.9550557136535645, "identity": 0.28990453481674194, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/es/c6052e7987ed9ed797a6d24e.mp3" }, { "key": "original-emo_Teasing-es-0-seed1701-scale1.0", "bucket": "emo_Teasing", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "bc91275cd4edeab30ffb15a7b62d3923ce75a41ab704032a3081da4c004a9823", "task_id": "emo_Teasing-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.0556148886680603, "target_z": -0.5312500207724515, "ce": 6.260893821716309, "genuineness": 4.231201171875, "identity": 0.41463524103164673, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/es/ac9ab07a9bead99e4cd50ee6.mp3" }, { "key": "original-emo_Teasing-es-0-seed1702-scale0.0", "bucket": "emo_Teasing", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "74ee839a72012f322731917cbba4a3844e990d308894818b0baf18b1094c7be7", "task_id": "emo_Teasing-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.09344401955604553, "target_z": -0.4609374878827366, "ce": 6.070269584655762, "genuineness": 4.369274139404297, "identity": 0.5153900384902954, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/es/6efc60e2695ff7a2d827618d.mp3" }, { "key": "original-emo_Teasing-es-0-seed1702-scale0.5", "bucket": "emo_Teasing", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "12c7d7d58b36d8c6101b1e6cb71d19a7f36733277385d15157aa02ba68071ceb", "task_id": "emo_Teasing-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.053513288497924805, "target_z": -0.5351562387482554, "ce": 6.078212261199951, "genuineness": 4.337893962860107, "identity": 0.7000834345817566, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/es/cc679be0c9c7b08087b9bdba.mp3" }, { "key": "original-emo_Teasing-es-0-seed1702-scale0.75", "bucket": "emo_Teasing", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "0194248db47224aa25b0d6967dc09a2c610520aef0e724e35f89e6d1f377cf40", "task_id": "emo_Teasing-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.27050527930259705, "target_z": -0.1318359368508609, "ce": 6.109982967376709, "genuineness": 3.9927117824554443, "identity": 0.4916521906852722, "hypothesis": "La puerta sigue abierta. He dejado tu abrijo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/es/1cbd905c90cda374c2733303.mp3" }, { "key": "original-emo_Teasing-es-0-seed1702-scale1.0", "bucket": "emo_Teasing", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "6fed9a3915981e4eed43c885d0397ab0351a6866264987cb471ffd47a806549a", "task_id": "emo_Teasing-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.09554563462734222, "target_z": -0.45703124221033065, "ce": 6.054384231567383, "genuineness": 4.017816066741943, "identity": 0.5335224866867065, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/es/79131d0a383dd4a69a090bf0.mp3" }, { "key": "original-emo_Teasing-es-1-seed1701-scale0.0", "bucket": "emo_Teasing", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "20d3dfdfe7c57d28cd2bd7737ff7f65ab25c81f8a3d2afc2f33c4ed7d34c1d11", "task_id": "emo_Teasing-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.08503752946853638, "target_z": -0.4765625259655645, "ce": 6.109982967376709, "genuineness": 4.720732688903809, "identity": 0.5789473652839661, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/es/d88a3a976e688bfe09360130.mp3" }, { "key": "original-emo_Teasing-es-1-seed1701-scale0.5", "bucket": "emo_Teasing", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "34817901cda349b1b9ebc6133ebe57566302d6ef5739cb470b5759dd39c0d21a", "task_id": "emo_Teasing-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.09554563462734222, "target_z": -0.45703124221033065, "ce": 6.1020402908325195, "genuineness": 4.557555198669434, "identity": 0.7445019483566284, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/es/ca7fa9368e26b1aaf8e08596.mp3" }, { "key": "original-emo_Teasing-es-1-seed1701-scale0.75", "bucket": "emo_Teasing", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "051d5635f4e21a1ba64f2c84e99c21492bcf5071c6312e9d2f58da8acb0b6b38", "task_id": "emo_Teasing-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.059818148612976074, "target_z": -0.5234374740344355, "ce": 6.149696350097656, "genuineness": 4.632867813110352, "identity": 0.5331987142562866, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/es/02d0f218c4ab7b3f0280368e.mp3" }, { "key": "original-emo_Teasing-es-1-seed1701-scale1.0", "bucket": "emo_Teasing", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "c6794deb331870d5470d36109de7ba49e18b85a6ac757735347de702e016a855", "task_id": "emo_Teasing-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.12812070548534393, "target_z": -0.3964843650465336, "ce": 6.125868320465088, "genuineness": 4.7834930419921875, "identity": 0.6312921047210693, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/es/e719ace269b618c32f42ca20.mp3" }, { "key": "original-emo_Teasing-es-1-seed1702-scale0.0", "bucket": "emo_Teasing", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "f1f566e74815578accce0e7e90f70692adf389a1e68f9e0a3298b9024022a7ea", "task_id": "emo_Teasing-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.17225466668605804, "target_z": -0.31445312283620297, "ce": 6.117925643920898, "genuineness": 4.632867813110352, "identity": 0.3600139319896698, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/es/6cf55fe4f0134b8658271a5e.mp3" }, { "key": "original-emo_Teasing-es-1-seed1702-scale0.5", "bucket": "emo_Teasing", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "ef4585752080f1701a7413f34c7ab073d0fc6dd310bf38c83fe333ac56bf4935", "task_id": "emo_Teasing-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.1228666603565216, "target_z": -0.40624999307584947, "ce": 6.332377910614014, "genuineness": 4.6705241203308105, "identity": 0.5806981921195984, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/es/ad236f8ea69f64b7a3baa8ac.mp3" }, { "key": "original-emo_Teasing-es-1-seed1702-scale0.75", "bucket": "emo_Teasing", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "b169552704141261fc5cb60bbcecfc3a8bdabfc366c556d90c24bb1bb8e39671", "task_id": "emo_Teasing-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.12076504528522491, "target_z": -0.4101562387482554, "ce": 6.070269584655762, "genuineness": 4.6203155517578125, "identity": 0.6483789682388306, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/es/09a1b0150c64026513a5e18f.mp3" }, { "key": "original-emo_Teasing-es-1-seed1702-scale1.0", "bucket": "emo_Teasing", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "cb9c7d5015f1674368079de3e335e64f6abf8554217da06529c29085d2bd0368", "task_id": "emo_Teasing-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.11656180024147034, "target_z": -0.41796875778966935, "ce": 6.046441555023193, "genuineness": 4.595211505889893, "identity": 0.6505435109138489, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/es/703cf012f7afc75a7f41bfbb.mp3" }, { "key": "original-emo_Teasing-fr-0-seed1701-scale0.0", "bucket": "emo_Teasing", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "2652a2596a4d6551baa053a9c9b980da9383807e95d98a5ccdaa741787795169", "task_id": "emo_Teasing-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.09764724969863892, "target_z": -0.45312499653792476, "ce": 6.133810997009277, "genuineness": 4.293961524963379, "identity": 0.6231728196144104, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/fr/ada09a6135190f8f491a4525.mp3" }, { "key": "original-emo_Teasing-fr-0-seed1701-scale0.5", "bucket": "emo_Teasing", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "75dbd2838290fe2583dc17f9c28a9c1b26f03d0b7adc18f66be99b85a4ebb1cc", "task_id": "emo_Teasing-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.10815533995628357, "target_z": -0.433593740479293, "ce": 6.117925643920898, "genuineness": 4.507347106933594, "identity": 0.6693140268325806, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/fr/d99683faca4f09a8605f74ac.mp3" }, { "key": "original-emo_Teasing-fr-0-seed1701-scale0.75", "bucket": "emo_Teasing", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "9e62f58f514c8095486aa773c5a7bcdccc56a97b6f173cf3d61e794924db78fb", "task_id": "emo_Teasing-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.10815533995628357, "target_z": -0.433593740479293, "ce": 6.054384231567383, "genuineness": 4.268857479095459, "identity": 0.6624033451080322, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/fr/81ffb5b391819b3633dd8ffa.mp3" }, { "key": "original-emo_Teasing-fr-0-seed1701-scale1.0", "bucket": "emo_Teasing", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "46f360495d94d0aac398f5a28e9636de52afab7d87ca2509d1215cb1209a2523", "task_id": "emo_Teasing-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.09134238958358765, "target_z": -0.4648437612517446, "ce": 6.125868320465088, "genuineness": 4.3127899169921875, "identity": 0.8118259906768799, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/fr/a751980145bdfeb93f27f723.mp3" }, { "key": "original-emo_Teasing-fr-0-seed1702-scale0.0", "bucket": "emo_Teasing", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "26037947c0d62427ea34b6715185a7c9e7a2e89ee4b1a25b006049b34e151bec", "task_id": "emo_Teasing-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.08924078941345215, "target_z": -0.4687499792275484, "ce": 6.181467056274414, "genuineness": 4.394378662109375, "identity": 0.7379586696624756, "hypothesis": "La porte était 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/audio/emo_Teasing/fr/305778542d931db37049db7a.mp3" }, { "key": "original-emo_Teasing-fr-0-seed1702-scale0.5", "bucket": "emo_Teasing", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "2f73843c4d98b2638a70bbb4a6c5102acc20db386e598dbfc3d84e7a26a8c801", "task_id": "emo_Teasing-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.19327083230018616, "target_z": -0.2753906384155416, "ce": 6.181467056274414, "genuineness": 4.168440818786621, "identity": 0.5288610458374023, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/fr/56334aaa03d02190f406ab2f.mp3" }, { "key": "original-emo_Teasing-fr-0-seed1702-scale0.75", "bucket": "emo_Teasing", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "b6bc393e18ecd17950364427fa61f711f33bb30cbd66a924a9835bea9be66e22", "task_id": "emo_Teasing-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.11551100015640259, "target_z": -0.41992186677757126, "ce": 6.213237762451172, "genuineness": 4.494794845581055, "identity": 0.6537820100784302, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/fr/bc286e25f9c3dd0ba180b56b.mp3" }, { "key": "original-emo_Teasing-fr-0-seed1702-scale1.0", "bucket": "emo_Teasing", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "099806540fe2b32c3d03311c7795b564f3ed187d998e92da32744442c5e4c64d", "task_id": "emo_Teasing-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.07452946901321411, "target_z": -0.496093726630992, "ce": 6.078212261199951, "genuineness": 4.3881025314331055, "identity": 0.7036660313606262, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/fr/89b9959173ab6501c3a40939.mp3" }, { "key": "original-emo_Teasing-fr-1-seed1701-scale0.0", "bucket": "emo_Teasing", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "15e22dd28696604a881e91567af9bc015c0ca1647e56c48739cfb5d3bde1beba", "task_id": "emo_Teasing-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.07242783904075623, "target_z": -0.5, "ce": 6.062326908111572, "genuineness": 4.457139015197754, "identity": 0.8660943508148193, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/fr/d0f4bd2e34826ac23d08cc77.mp3" }, { "key": "original-emo_Teasing-fr-1-seed1701-scale0.5", "bucket": "emo_Teasing", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "138fc6375c8e49ee104a99b6214d2733b7a173dd3253b38c0d7e3c70428bedf5", "task_id": "emo_Teasing-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.1249682754278183, "target_z": -0.40234374740344353, "ce": 6.23706579208374, "genuineness": 4.432034492492676, "identity": 0.7545438408851624, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/fr/07fdae485aea6f6c6dc811a2.mp3" }, { "key": "original-emo_Teasing-fr-1-seed1701-scale0.75", "bucket": "emo_Teasing", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "95838e0c3b181915e5ee19a86abf0a6ed5a635e80c462b03240ba09fca682a26", "task_id": "emo_Teasing-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.03880196809768677, "target_z": -0.5624999861516989, "ce": 6.022613525390625, "genuineness": 4.3504462242126465, "identity": 0.7702099084854126, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/fr/3cb01adc04499a532bd0d88a.mp3" }, { "key": "original-emo_Teasing-fr-1-seed1701-scale1.0", "bucket": "emo_Teasing", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "2ac8d0cb6fc9fed372b885a3f52f9ac6b18dd81d7b04ba43c42ffdd37b55efca", "task_id": "emo_Teasing-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.11446018517017365, "target_z": -0.42187500346207524, "ce": 6.086154937744141, "genuineness": 4.545003414154053, "identity": 0.7599977850914001, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/fr/991b5719016b6861d614b182.mp3" }, { "key": "original-emo_Teasing-fr-1-seed1702-scale0.0", "bucket": "emo_Teasing", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "47b11cb187da1b6c0cbf4f51ea5e7fc85caf0c809f09a30f3ae87923d02bbc16", "task_id": "emo_Teasing-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.18591517210006714, "target_z": -0.2890625121172634, "ce": 6.260893821716309, "genuineness": 4.645420074462891, "identity": 0.7674775719642639, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/fr/0c70ae42a4dd8b1fc725f48a.mp3" }, { "key": "original-emo_Teasing-fr-1-seed1702-scale0.5", "bucket": "emo_Teasing", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "290aed0ad739ccdf26da5c4b777b66652b2f93d3504b20cabc96806325de664b", "task_id": "emo_Teasing-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.11130775511264801, "target_z": -0.4277343858189852, "ce": 6.24500846862793, "genuineness": 4.909013748168945, "identity": 0.753912627696991, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/fr/844616c86a9a32d31bb1584e.mp3" }, { "key": "original-emo_Teasing-fr-1-seed1702-scale0.75", "bucket": "emo_Teasing", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "0b25ed07c6f2a3cde05e3b4da7b2875db7869f2f884ca8e350a24040b406e244", "task_id": "emo_Teasing-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.07663106918334961, "target_z": -0.4921875086551882, "ce": 6.109982967376709, "genuineness": 4.65797233581543, "identity": 0.6023565530776978, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/fr/219281f89acae62d78c01d86.mp3" }, { "key": "original-emo_Teasing-fr-1-seed1702-scale1.0", "bucket": "emo_Teasing", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "cb1665d8b09388493d076904b8b22c79643dfcef6173e5ea9b7f5dd328ae675f", "task_id": "emo_Teasing-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.1018504798412323, "target_z": -0.4453125051931129, "ce": 6.117925643920898, "genuineness": 4.570107460021973, "identity": 0.7450978755950928, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/fr/c6ab677b1de170b3dadf7c35.mp3" }, { "key": "original-emo_Teasing-nl-0-seed1701-scale0.0", "bucket": "emo_Teasing", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "662f8580c9c8160b573fe5645af6ba657538d468db3edd1d0b4679a502c341e1", "task_id": "emo_Teasing-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2367238998413086, "target_z": 1.6640625398138655, "ce": 6.23706579208374, "genuineness": 4.18099308013916, "identity": 0.7127106189727783, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/nl/ec61b4c9d0b41462fa81eb33.mp3" }, { "key": "original-emo_Teasing-nl-0-seed1701-scale0.5", "bucket": "emo_Teasing", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "e03ce5ade90d8b63a66a5b73f188650efa8032f5201d5261be347aa36a8c3cb9", "task_id": "emo_Teasing-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.9382941722869873, "target_z": 1.1093749342205699, "ce": 6.157639026641846, "genuineness": 4.306513786315918, "identity": 0.6407212018966675, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/nl/773da06c14b758b3b6d65484.mp3" }, { "key": "original-emo_Teasing-nl-0-seed1701-scale0.75", "bucket": "emo_Teasing", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "8998d7d848717103ce203d8f1f8da846fdc984a8dbb6b454fce2f5916f2ac804", "task_id": "emo_Teasing-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.15228930115699768, "target_z": -0.35156249826896235, "ce": 5.927301406860352, "genuineness": 4.281409740447998, "identity": 0.6322178244590759, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je 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_Teasing/nl/7b98c90588662e5de0c8eb08.mp3" }, { "key": "original-emo_Teasing-nl-0-seed1701-scale1.0", "bucket": "emo_Teasing", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "9ec822dd5cf1a026f368b8968ec086cb6160dc6571c1ffa771567d97bdc199f5", "task_id": "emo_Teasing-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.6987098455429077, "target_z": 0.6640625398138655, "ce": 6.149696350097656, "genuineness": 4.362998008728027, "identity": 0.6969132423400879, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/nl/92acf31f4ab1dcd9c0b89dc7.mp3" }, { "key": "original-emo_Teasing-nl-0-seed1702-scale0.0", "bucket": "emo_Teasing", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "4cd862f054adfd734af81bac972db633f30a21e2e5abe1d336af4e7bae195af1", "task_id": "emo_Teasing-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.20062650740146637, "target_z": -0.26171873701721776, "ce": 6.0146708488464355, "genuineness": 4.193545341491699, "identity": 0.48243722319602966, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/nl/89833bd6a2f858fa7f6cb926.mp3" }, { "key": "original-emo_Teasing-nl-0-seed1702-scale0.5", "bucket": "emo_Teasing", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "29af47b5843247ed29799d3ee4928c1f28d0ea237022f321baae5eb79fbb4f0f", "task_id": "emo_Teasing-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.15334011614322662, "target_z": -0.3496093615844584, "ce": 5.982900142669678, "genuineness": 4.293961524963379, "identity": 0.5452765226364136, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/nl/cbda97687d3b9a01a3115ad0.mp3" }, { "key": "original-emo_Teasing-nl-0-seed1702-scale0.75", "bucket": "emo_Teasing", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "03eaced2e0dbebd2a001717eb448012c474c3d49a676eced9ab5b22e27d080c9", "task_id": "emo_Teasing-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0727977752685547, "target_z": 1.3593751004001826, "ce": 6.1020402908325195, "genuineness": 4.419482707977295, "identity": 0.7833821773529053, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/nl/9b1ea7bbee87c4ef5c7b851f.mp3" }, { "key": "original-emo_Teasing-nl-0-seed1702-scale1.0", "bucket": "emo_Teasing", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "f093dfd2f7b720bcad7cc359982c180dcb0c6a59f9e9525195653dc6413f5392", "task_id": "emo_Teasing-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.44809195399284363, "target_z": 0.19824219637156787, "ce": 6.133810997009277, "genuineness": 4.243753433227539, "identity": 0.630977213382721, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg, maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/nl/7f85fa499559ca0b91a8a832.mp3" }, { "key": "original-emo_Teasing-nl-1-seed1701-scale0.0", "bucket": "emo_Teasing", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "575f090550790560b1f40fbf8fea0379aec4d0231b6fe42d26bbdef018292f83", "task_id": "emo_Teasing-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.5494949817657471, "target_z": 0.38671873701721776, "ce": 6.133810997009277, "genuineness": 4.482243061065674, "identity": 0.48687034845352173, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/nl/ec5aebf4d4911962a456aa69.mp3" }, { "key": "original-emo_Teasing-nl-1-seed1701-scale0.5", "bucket": "emo_Teasing", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "27fd83d5437a42ffa71c03e2974bbcc0c2cf835e1ede6ff712ff81d2e6e9f86d", "task_id": "emo_Teasing-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 1.5183405876159668, "target_z": 2.187499958455097, "ce": 6.109982967376709, "genuineness": 4.2249250411987305, "identity": 0.6842414140701294, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/nl/b0fca70d2099a05b4a90169a.mp3" }, { "key": "original-emo_Teasing-nl-1-seed1701-scale0.75", "bucket": "emo_Teasing", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "93ce1ae3518625b60618d5b28fd0df745579bb2e28b15c74e47ad43309e66076", "task_id": "emo_Teasing-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.48224323987960815, "target_z": 0.2617187647138199, "ce": 6.205295085906982, "genuineness": 4.18099308013916, "identity": 0.7151474952697754, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/nl/0c8c6dbcedb51932012472f3.mp3" }, { "key": "original-emo_Teasing-nl-1-seed1701-scale1.0", "bucket": "emo_Teasing", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "cb487644f0a897a0e4f30527427773399369cf94e94d64737315d51001b69a80", "task_id": "emo_Teasing-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.602035403251648, "target_z": 0.4843749619171721, "ce": 6.0146708488464355, "genuineness": 4.017816066741943, "identity": 0.6469937562942505, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/nl/3e2c4c76a2cea5bd8fcff600.mp3" }, { "key": "original-emo_Teasing-nl-1-seed1702-scale0.0", "bucket": "emo_Teasing", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "89cb943bbe154fa2c9f78fddbab2424be9cb066ad2579b5e561b0e2595221213", "task_id": "emo_Teasing-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.476989209651947, "target_z": 0.25195316438110615, "ce": 6.149696350097656, "genuineness": 4.262581825256348, "identity": 0.6960949897766113, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/nl/2f5ab0ce08e40bc2996af4a2.mp3" }, { "key": "original-emo_Teasing-nl-1-seed1702-scale0.5", "bucket": "emo_Teasing", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "9be0473f2c163b19944f465110779b684b78dec134e892be792330572cd4f172", "task_id": "emo_Teasing-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.45912545919418335, "target_z": 0.21875003462075265, "ce": 6.165581703186035, "genuineness": 4.482243061065674, "identity": 0.44303494691848755, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/nl/5e991b870a38ebbbeb07eb2f.mp3" }, { "key": "original-emo_Teasing-nl-1-seed1702-scale0.75", "bucket": "emo_Teasing", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "ea67905611fd63a74146801a2ceb121a24b1e3a1826f85e29f901d3f2e2ff837", "task_id": "emo_Teasing-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.09239320456981659, "target_z": -0.4628906245672406, "ce": 6.086154937744141, "genuineness": 4.331617832183838, "identity": 0.6174638271331787, "hypothesis": "Ik heb een kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/nl/729260596ca99f0d98de9681.mp3" }, { "key": "original-emo_Teasing-nl-1-seed1702-scale1.0", "bucket": "emo_Teasing", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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 Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bb9f5c2de0946ef504edc0b7de03a7e4150ede270994dc403c3387b4433f7fb6", "mp3_sha256": "668b0606796e7e78bdab7640bd80371a79ae0559997694c95b49c9caf20f25d7", "task_id": "emo_Teasing-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Teasing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Teasing. 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 Teasing. 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 Teasing. 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": 0.364815354347229, "target_z": 0.04345702118834376, "ce": 6.229123115539551, "genuineness": 4.519899368286133, "identity": 0.732917070388794, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Teasing/nl/0cda6a4c8fe786a6b63f75c4.mp3" } ], "source_standard_audio_unchanged": true }