{ "complete": true, "report": { "bucket": "emo_Awe", "label": "Intense Awe", "definition": { "id": "emo_Awe", "category": "emotion", "head": "emo_Awe", "pole": "high", "label": "Intense Awe", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_awe/full-v2-sealed/sealed-selected", "mission": "emotion_awe", "format_status": "CANONICAL", "heldout": true, "qualified": true, "source_cfg": 3, "source_model": { "label": "Humaneness 1.5 + real-speech rank 4", "repo": "laion/Humaneness-Voice-Large-1.5-RealSpeech-LoRAs", "revision": "fed33e554f094fcdc89fc0124aed2f9d42018714", "rank": 4 }, "metrics": { "ce": 6.36978777885437, "genuineness": 4.466050758361816, "wer": 0.008753360215053763, "identity": 0.5796130573749543, "voiceclap": -0.007210869090631605, "fitness": 0.7464723175360272, "steering_v2": 0.8138562464459259, "raw_target": 0.7517241938412189, "target_cdf": 0.8138562464459259, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.355252733230591, "genuineness": 4.424754428863525, "wer": 0.009721774193548386, "identity": 0.5796130573749543, "fitness": 0.745381184635509, "steering_v2": 0.8171917747220314 }, "none": { "n": 50, "ce": 6.38432282447815, "genuineness": 4.507347087860108, "wer": 0.0077849462365591395, "identity": null, "fitness": 0.7475634504365455, "steering_v2": 0.8105207181698203 } } } } ], "selected_wording": { "id": "manual-51b69a70d1d3", "general": "Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.", "inline": [ "Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.", "Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.", "Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence." ], "cfg": 3, "recipe": "P09", "strategy": "initial-physical-directing", "timing_syntax": "canonical", "canonical_labels": true, "neutral_event": "keep", "parent": "cfg-3", "origin": "exact_frozen_manual_recipe" }, "selection": { "manual_no_adapter": { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 2.254101574674797, "target_raw": 1.0643842585384846, "ce": 6.11077733039856, "genuineness": 4.563517689704895, "identity": 0.5164559669792652, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.034069141000509263, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 2.2646484404119676, "target_raw": 1.0688115321099758, "ce": 5.945966839790344, "genuineness": 4.438624477386474, "identity": 0.5006956435739994, "wer": 0.01067251461988304, "valid_fraction": 0.95, "identity_delta": -0.04982946440577507, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 2.254101574674797, "target_raw": 1.0643842585384846, "ce": 6.11077733039856, "genuineness": 4.563517689704895, "identity": 0.5164559669792652, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.034069141000509263, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": 2.0228027547934375, "target_raw": 0.9672916077077389, "ce": 6.191593956947327, "genuineness": 4.567283320426941, "identity": 0.5577288955450058, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.007203787565231323, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": 1.4872070647376245, "target_raw": 0.7424638055264949, "ce": 6.190402603149414, "genuineness": 4.5503379821777346, "identity": 0.5343335874378681, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.016191520541906358, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": 1.3850097831453367, "target_raw": 0.6995643001049757, "ce": 6.235874366760254, "genuineness": 4.460590600967407, "identity": 0.5653063431382179, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.014781235158443451, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": 1.0403320509820453, "target_raw": 0.5548784140497446, "ce": 6.231903004646301, "genuineness": 4.4238758206367494, "identity": 0.5515632435679436, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.001038135588169098, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": 0.9493164204909069, "target_raw": 0.5166726469993591, "ce": 6.227534532546997, "genuineness": 4.46341483592987, "identity": 0.5507137164473533, "wer": 0.003125, "valid_fraction": 1, "identity_delta": 0.00018860846757888793, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": 0.8476806833473504, "target_raw": 0.47400886192917824, "ce": 6.218003368377685, "genuineness": 4.427327585220337, "identity": 0.5472076088190079, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.0033174991607666016, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 1.9959961067983871, "target_raw": 0.9560389410704374, "ce": 6.00216121673584, "genuineness": 4.507347130775452, "identity": 0.4622968897223473, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": -0.08822821825742722, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 2.2646484404119676, "target_raw": 1.0688115321099758, "ce": 5.945966839790344, "genuineness": 4.438624477386474, "identity": 0.5006956435739994, "wer": 0.01067251461988304, "valid_fraction": 0.95, "identity_delta": -0.04982946440577507, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": 2.060839886195391, "target_raw": 0.9832585111260415, "ce": 6.156447625160217, "genuineness": 4.55912446975708, "identity": 0.5251731857657432, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.02535192221403122, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 2.018359397463748, "target_raw": 0.9654264129698277, "ce": 6.055377125740051, "genuineness": 4.533078837394714, "identity": 0.5127936229109764, "wer": 0.0029411764705882353, "valid_fraction": 1, "identity_delta": -0.03773148506879807, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 1.8770996471543098, "target_raw": 0.9061295967549086, "ce": 5.913401865959168, "genuineness": 4.429838037490844, "identity": 0.5148275412619114, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.03569756671786308, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 1.8728516092856087, "target_raw": 0.9043463915586472, "ce": 5.968801999092102, "genuineness": 4.50609188079834, "identity": 0.5228350669145584, "wer": 0.005902777777777778, "valid_fraction": 1, "identity_delta": -0.027690041065216064, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 1.7198730604988473, "target_raw": 0.8401303578168153, "ce": 6.138973736763001, "genuineness": 4.584856104850769, "identity": 0.5275893107056617, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.022935797274112702, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": 1.5628906158481026, "target_raw": 0.7742336027324199, "ce": 6.198146677017212, "genuineness": 4.530882263183594, "identity": 0.533027396351099, "wer": 0.01111111111111111, "valid_fraction": 0.95, "identity_delta": -0.01749771162867546, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": 1.498339879095737, "target_raw": 0.7471370436251163, "ce": 6.203706550598144, "genuineness": 4.453373146057129, "identity": 0.5622158899903298, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.011690782010555267, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": 1.467822319309198, "target_raw": 0.7343266420066357, "ce": 6.223960375785827, "genuineness": 4.556614065170288, "identity": 0.5685515344142914, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": 0.018026426434516907, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": 1.4186523770989594, "target_raw": 0.7136865019798279, "ce": 6.217407655715943, "genuineness": 4.530882215499878, "identity": 0.5263184197247028, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.02420668825507164, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": 1.4126953061491379, "target_raw": 0.7111858934164047, "ce": 6.231505918502807, "genuineness": 4.5327650785446165, "identity": 0.5396613694727421, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.010863738507032395, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": 1.2004394801022975, "target_raw": 0.6220869485288858, "ce": 6.232697296142578, "genuineness": 4.440193462371826, "identity": 0.5589180573821068, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.008392949402332307, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": 1.168945329666741, "target_raw": 0.6088666019961237, "ce": 6.26009955406189, "genuineness": 4.450862717628479, "identity": 0.5744567185640335, "wer": 0.010526315789473684, "valid_fraction": 0.95, "identity_delta": 0.023931610584259033, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": 1.1094238425115053, "target_raw": 0.5838811784982681, "ce": 6.215223407745361, "genuineness": 4.448352313041687, "identity": 0.5264709562063217, "wer": 0.013888888888888888, "valid_fraction": 0.95, "identity_delta": -0.02405415177345276, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": 1.097363300427385, "target_raw": 0.5788185067474843, "ce": 6.233094429969787, "genuineness": 4.459335422515869, "identity": 0.5603458642959595, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.009820756316184998, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": 1.025927733938205, "target_raw": 0.5488318923860789, "ce": 6.192983937263489, "genuineness": 4.411009955406189, "identity": 0.5793099947273731, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": 0.02878488674759865, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": 0.982763697645911, "target_raw": 0.5307128604501485, "ce": 6.219591903686523, "genuineness": 4.4408210754394535, "identity": 0.5605896569788456, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.01006454899907112, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": 0.929980478082162, "target_raw": 0.5085559695959091, "ce": 6.194969606399536, "genuineness": 4.415716910362244, "identity": 0.559102064371109, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": 0.008576956391334534, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": 0.8177734404119673, "target_raw": 0.4614546539261937, "ce": 6.228924489021301, "genuineness": 4.449293780326843, "identity": 0.579125241190195, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.028600133210420608, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": 0.8012695307924051, "target_raw": 0.4545267831534147, "ce": 6.2398456811904905, "genuineness": 4.431720852851868, "identity": 0.5667843110859394, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.01625920310616493, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 2.050683595483314, "target_raw": 0.9789951898157596, "ce": 5.998785591125488, "genuineness": 4.493853664398193, "identity": 0.49957080744206905, "wer": 0.01929824561403509, "valid_fraction": 0.95, "identity_delta": -0.05095430053770542, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 2.0240234355309554, "target_raw": 0.9678040146827698, "ce": 6.015465188026428, "genuineness": 4.515819787979126, "identity": 0.4914050601422787, "wer": 0.0059649122807017545, "valid_fraction": 1, "identity_delta": -0.059120047837495804, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 1.8829590082323324, "target_raw": 0.9085891894996166, "ce": 6.163198924064636, "genuineness": 4.5487689733505245, "identity": 0.4911153443157673, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.05940976366400719, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 1.7793457353161057, "target_raw": 0.8650952912867069, "ce": 6.176502895355225, "genuineness": 4.512681698799133, "identity": 0.48412718027830126, "wer": 0.007894736842105263, "valid_fraction": 0.95, "identity_delta": -0.06639792770147324, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": 0.5090332204512057, "target_raw": 0.33185431100428103, "ce": 6.194572472572327, "genuineness": 4.412265110015869, "identity": 0.5505251079797745, "wer": 0.00625, "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": 0.5958496103248561, "target_raw": 0.3682973565533757, "ce": 6.186629796028138, "genuineness": 4.329735112190247, "identity": 0.5377704426646233, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.012754665315151214, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": 0.5642578130269275, "target_raw": 0.35503602065145967, "ce": 6.1854383707046505, "genuineness": 4.320007371902466, "identity": 0.53781298995018, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.012712118029594422, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": 0.5813476575118526, "target_raw": 0.36220985017716884, "ce": 6.202912282943726, "genuineness": 4.32816618680954, "identity": 0.551145538687706, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0006204307079315186, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": 0.2113085948620942, "target_raw": 0.2068780005723238, "ce": 6.273919725418091, "genuineness": 4.3545882654190065, "identity": 0.5631067588925361, "wer": 0.006967418546365915, "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": 1.6400684119082776, "target_raw": 0.8066306413710117, "ce": 6.142389135360718, "genuineness": 4.478226251602173, "identity": 0.5230773529410362, "wer": 0.010574534161490682, "valid_fraction": 1, "identity_delta": -0.04002940595149994, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 1.914980507545725, "target_raw": 0.9220309020578861, "ce": 6.0666160392761235, "genuineness": 4.436804404258728, "identity": 0.5165845075249672, "wer": 0.010848861283643893, "valid_fraction": 1, "identity_delta": -0.04652225136756897, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 1.8679101807188456, "target_raw": 0.9022721207141876, "ce": 6.058117361068725, "genuineness": 4.417474193572998, "identity": 0.5263149186968803, "wer": 0.011887351778656127, "valid_fraction": 1, "identity_delta": -0.036791840195655824, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": 0.04707032682687929, "ci95_z": [ -0.22337888636819633, 0.30080079692193085 ], "language_deltas": { "en": 0.1895507722506342, "de": 0.30390626320091857, "fr": 0.3533203429785915, "nl": -0.20673826892267155, "es": -0.40468747537307626 }, "languages_improved": 3, "clear_gain": false, "delta_ce": 0.008498678207397461, "delta_genuineness": 0.01933021068572998, "delta_wer": -0.001038490495012234, "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": 0.2749120956374473, "ci95_z": [ 0.1918456827786681, 0.35797850849622653 ], "language_deltas": { "en": 0.37499999645017307, "de": 0.3976562481141544, "fr": 0.1948242104439597, "nl": 0.24458005335247773, "es": 0.16249996982647164 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.07577309608459473, "delta_genuineness": -0.041421847343444826, "delta_wer": 0.00027432712215320914, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 1.4287598170461833, "ci95_z": [ 1.093085990153916, 1.7775977253135455 ], "language_deltas": { "en": 1.5014648751021817, "de": 1.3291016030734117, "fr": 1.4325195822648946, "nl": 0.8615723086597173, "es": 2.0191407161307113 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.13153059005737305, "delta_genuineness": 0.1236379861831665, "delta_wer": 0.0036071156151247685, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 4.0, "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain" }, "reference_only": true, "updated": 1793025216.2705348, "example": { "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.", "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." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [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.", "language": "de", "seed": 1701, "scale": 0.0, "cfg": 4.0, "frames": 128, "reference": true } }, "rows": [ { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "006bd7307bbe41cbcd15cb3e3de449020a432223b56b8cae799ee41622be04e5", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3bdcbceffd9467f683a6b8f1242c6a1ac1dc0f6d6c660687fb93d5594838a4b3", "generation_seconds_batch": 17.36622269405052, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9183661341667175, "target_z": 1.9062501198066566, "ce": 5.7247633934021, "genuineness": 4.331617832183838, "identity": 0.37871575355529785, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/006bd7307bbe41cbcd15cb3e3de449020a432223b56b8cae799ee41622be04e5.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": "007ba3d9f3b10a3d0efdd0d74cdec6a708fc987f2fde37b35df451e302e5310b", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ae5b29780446ed6e01b8a34fdd64040e183c6740419aeb889a410bf80442ca88", "generation_seconds_batch": 17.219452708028257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2331947088241577, "target_z": 2.6562500133118507, "ce": 5.8875885009765625, "genuineness": 4.494794845581055, "identity": 0.7709139585494995, "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_Awe/007ba3d9f3b10a3d0efdd0d74cdec6a708fc987f2fde37b35df451e302e5310b.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "015489af9e7dde5882191b118112697b91b1519e9b49aaa68b55dac275605665", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b669af7cc0a48d673d93b1ad5a35985bd305160e1fcde487f3513269649bb776", "generation_seconds_batch": 21.465720435022376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.138327121734619, "target_z": 4.8125003283589844, "ce": 6.0305562019348145, "genuineness": 4.607763767242432, "identity": 0.28571608662605286, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/015489af9e7dde5882191b118112697b91b1519e9b49aaa68b55dac275605665.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "01c60332ca0d2757ad02f21ffbe1b0d333884c90509a6d1b824aa8f056e3f388", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3bfbe8d8076cad3cedf5a1f45194aef11e4571a61ba50f10a54e05ff5e9bdc41", "generation_seconds_batch": 29.54347494605463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35101866722106934, "target_z": 0.554687478922903, "ce": 6.2767791748046875, "genuineness": 4.18099308013916, "identity": 0.2835921049118042, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/01c60332ca0d2757ad02f21ffbe1b0d333884c90509a6d1b824aa8f056e3f388.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "d8136a62e36affa09ffa48cd6bc7a3c5a854511805f22020869645e9a9629f81", "generation_seconds_batch": 17.291537005919963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14646205306053162, "target_z": 0.06738279572152148, "ce": 6.070269584655762, "genuineness": 4.243753433227539, "identity": 0.7102065682411194, "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_Awe/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "0205b27ba15720d4b3968f76d2d158b156466867b3f42e8657290e48efe54e56", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3979602b6ddda3431eeaecc55a604c52c7e6464d0220bf191e3bcf15b763ae97", "generation_seconds_batch": 24.59099932794925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3395405411720276, "target_z": 0.5273437305868843, "ce": 6.252951145172119, "genuineness": 4.557555198669434, "identity": 0.5617737770080566, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0205b27ba15720d4b3968f76d2d158b156466867b3f42e8657290e48efe54e56.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": "025331d7425440063bcc7a090aa6dfb7b79e7b86682a3f2d42d489d943531db8", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "b3b644f9c7c2e5121bd4401bc018e7ed223913af53cf7e499560dec5799b917e", "generation_seconds_batch": 18.066441425005905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.764231264591217, "target_z": 1.5390625610126492, "ce": 6.157639026641846, "genuineness": 4.808597087860107, "identity": 0.5417740941047668, "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": 0.120000000000001, "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_Awe/025331d7425440063bcc7a090aa6dfb7b79e7b86682a3f2d42d489d943531db8.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": "028bfb85dfe79272aff4490cb146d7fa4f3e8ff6f0e2484b51019dbcbdd71ca5", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Your message arrived after I had left.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aa6da26291d799d0b3ce054e494235f408ee97dd7a007c297c6dea2cc458994a", "generation_seconds_batch": 16.92870921699796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.276410847902298, "target_z": 0.37695311473878174, "ce": 6.332377910614014, "genuineness": 4.557555198669434, "identity": 0.40611162781715393, "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_Awe/028bfb85dfe79272aff4490cb146d7fa4f3e8ff6f0e2484b51019dbcbdd71ca5.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": "029c0ca9acba573c1fcfb2fd5d12d3ce165f94d6363ddb0564ca86f45c6c8dd4", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "89bea388c6f2749d220608ec94f75e67f415de1c575c0cbde2478d7805ea274e", "generation_seconds_batch": 23.860637701000087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6920830607414246, "target_z": 1.3671876120414104, "ce": 6.086154937744141, "genuineness": 4.394378662109375, "identity": 0.4789907932281494, "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_Awe/029c0ca9acba573c1fcfb2fd5d12d3ce165f94d6363ddb0564ca86f45c6c8dd4.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "02ef421c70e7da3dcee8e2b6faa5b3ae01a33cb2a508a89efc0351aeb66e3289", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "51b9820049230c5f303226015b62a1fc559636eaf5b40e9b8016d97b2dc36e4f", "generation_seconds_batch": 22.564539704937488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2460758090019226, "target_z": 0.30468751442117165, "ce": 6.09409761428833, "genuineness": 4.7081804275512695, "identity": 0.7587272524833679, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/02ef421c70e7da3dcee8e2b6faa5b3ae01a33cb2a508a89efc0351aeb66e3289.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "035b3fc503cff8c8cb2ddf763eea7b260ae15ea4bf427c8609245ed16f07aea1", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0cc1023955a8d1228a56ed7e81202ff098c98a15f4f6e0d9f79ec72240d68da3", "generation_seconds_batch": 17.889424997963943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2641128599643707, "target_z": 0.34765625166398134, "ce": 6.086154937744141, "genuineness": 4.293961524963379, "identity": 0.3238215446472168, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/035b3fc503cff8c8cb2ddf763eea7b260ae15ea4bf427c8609245ed16f07aea1.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "03a75106c7dd02df8d6b81488c6e5bf7a77b2c0e9ef4cff27be5f25a203b2c28", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8727f48304da4fa09fba04acd60f6dca44770b5dc153365382595a8cafb1065b", "generation_seconds_batch": 24.195559829939157, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2120513617992401, "target_z": 0.2236328267825065, "ce": 6.2767791748046875, "genuineness": 4.074300289154053, "identity": 0.1697818785905838, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/03a75106c7dd02df8d6b81488c6e5bf7a77b2c0e9ef4cff27be5f25a203b2c28.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": "04641ce9ce51c45fe6aaa90a025294b0b08d9d392de88fab6a6a467342dfe5e1", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5f8583eafd84f3c1755505c28ccd12a2fc17c03157c06c5a1efa2bff32037751", "generation_seconds_batch": 17.110133982030675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3870927691459656, "target_z": 0.6406249534085224, "ce": 6.2767791748046875, "genuineness": 4.607763767242432, "identity": 0.5270459055900574, "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_Awe/04641ce9ce51c45fe6aaa90a025294b0b08d9d392de88fab6a6a467342dfe5e1.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "0506bb7f851a6961ddad7690d60403dae3a9e3d377bb6d0654ea388444443e1d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2299110e474ba07f5131db4b6a3740cdb385f1e2e75f257fee3eaa12e524d34c", "generation_seconds_batch": 17.641402338980697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7775858640670776, "target_z": 3.9531250155304924, "ce": 6.078212261199951, "genuineness": 4.482243061065674, "identity": 0.5673500895500183, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0506bb7f851a6961ddad7690d60403dae3a9e3d377bb6d0654ea388444443e1d.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "4e5f004ab6de1a94edca275831dcdcb96bcaf2853b469541db6960a1c589a4c0", "generation_seconds_batch": 15.923801847035065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.182946115732193, "target_z": 0.154296898573069, "ce": 6.443574905395508, "genuineness": 4.457139015197754, "identity": 0.6879984140396118, "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_Awe/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "0738435d0996e8d41cef86d09e71a4eab04a1088e2354fefd20c8e975657d6e8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7a955a9701f93e5989ab99cb02f31fe48eca7f1fa58730af086966f5c25ea517", "generation_seconds_batch": 17.524123965995386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08456216752529144, "target_z": -0.08007811252013994, "ce": 5.990842819213867, "genuineness": 4.331617832183838, "identity": 0.4992106556892395, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0738435d0996e8d41cef86d09e71a4eab04a1088e2354fefd20c8e975657d6e8.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": "07573cd74af7c2d78b94c71776efa0912ede574b89fd4c96ae84e94f3152d361", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dbcd8d4df521ed42f9d83f84aa21bdbb1dda4ab9bc87e86369c70c349590950f", "generation_seconds_batch": 18.518495627096854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5936990976333618, "target_z": 1.1328125654499328, "ce": 5.831989288330078, "genuineness": 4.2374773025512695, "identity": 0.6321355700492859, "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_Awe/07573cd74af7c2d78b94c71776efa0912ede574b89fd4c96ae84e94f3152d361.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "07778bee31660644801ac8f8237e07d42dab669640ded516dcd636d100c3f188", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "63b54f58f91fbb0b6f65051180fc3601b4b3bdd642ea0d7cffea02f49f1d21e9", "generation_seconds_batch": 17.69455434405245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7478339672088623, "target_z": 1.50000012424394, "ce": 6.332377910614014, "genuineness": 4.306513786315918, "identity": 0.4713892340660095, "hypothesis": "The 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_Awe/07778bee31660644801ac8f8237e07d42dab669640ded516dcd636d100c3f188.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "07c407a431b6cd419f69b2779f37862464bf7f5a169195c0b6bfaf6aec8d2c08", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "736d3d1af8c0c930a76fc342ceba7d60a7ab87f6ebf26ca646f55eb7b7799aac", "generation_seconds_batch": 24.765843049972318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4365215301513672, "target_z": 3.1406250244050598, "ce": 6.340320587158203, "genuineness": 4.457139015197754, "identity": 0.47714728116989136, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/07c407a431b6cd419f69b2779f37862464bf7f5a169195c0b6bfaf6aec8d2c08.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "07ed29174b54f3c08bfb5b242cc9af0e9e3c88490466f655c8c02cfc56da6f9e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8f7cc672f165c9a87180f0a75abae95303487384468757f8308374a436c7f830", "generation_seconds_batch": 24.186105314991437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8462178707122803, "target_z": 1.7343750288423432, "ce": 6.141753673553467, "genuineness": 4.18099308013916, "identity": 0.46453529596328735, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/07ed29174b54f3c08bfb5b242cc9af0e9e3c88490466f655c8c02cfc56da6f9e.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "083796c4fb398f8b2d72f1962fb4dbde75ffd310b6eb614d4a3c0ac4dbbe9ef3", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f6de7d175e6f7ebd98a6c9db48ff6606618b3c9e085903f9e3a9e24ed349aa68", "generation_seconds_batch": 23.902794518042356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22885861992835999, "target_z": 0.26367189191714363, "ce": 6.1020402908325195, "genuineness": 4.262581825256348, "identity": 0.6309160590171814, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/083796c4fb398f8b2d72f1962fb4dbde75ffd310b6eb614d4a3c0ac4dbbe9ef3.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "086306c2eeb9b51e48348a655571a164660be788e0216ec95118d3b65e20f7bb", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8d22c0ea77665579ce1cfa0721c2aba1a4ab913d04f2631920de901608a0fad8", "generation_seconds_batch": 21.108391446061432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.059619903564453, "target_z": 4.625000177491343, "ce": 6.395919322967529, "genuineness": 4.6203155517578125, "identity": 0.4335094094276428, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/086306c2eeb9b51e48348a655571a164660be788e0216ec95118d3b65e20f7bb.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "08c386457c537de2a8312245ffdeb49368282c69fd15af6958b5c5f7192a740b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "059fe5a0aacb6022b0a43d9530ea49e9f132dbfe7b3633dd8159f1682b56ad12", "generation_seconds_batch": 23.292711919988506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24115660786628723, "target_z": 0.292968754991944, "ce": 6.23706579208374, "genuineness": 4.432034492492676, "identity": 0.5389296412467957, "hypothesis": "Ik had dat uit ootje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.2222222222222222, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/08c386457c537de2a8312245ffdeb49368282c69fd15af6958b5c5f7192a740b.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "08c45796300314036ddd33c2e14ef6709254b921200341fe4a48945e5092d573", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "91a98940580aa81264472e68d4a1073d68957fd60e7dfe6339d94050ffcb1792", "generation_seconds_batch": 23.315608681063168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6792019605636597, "target_z": 3.7187501109320893, "ce": 6.173524379730225, "genuineness": 4.6203155517578125, "identity": 0.42494577169418335, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/08c45796300314036ddd33c2e14ef6709254b921200341fe4a48945e5092d573.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "0959c30ad4f2a272a141efdbbd58dbc047b89a9fdb26a40a4127988e489c772e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "73213b9ed44c1924e472de376dd3306a82a1a5dcbba41dc8b3c9555ce50851fd", "generation_seconds_batch": 17.41929367906414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8396589756011963, "target_z": 1.7187501109320893, "ce": 6.403861999511719, "genuineness": 4.20609712600708, "identity": 0.4225924015045166, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0959c30ad4f2a272a141efdbbd58dbc047b89a9fdb26a40a4127988e489c772e.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "096be7e73fd74737a8c0acd16911a6dccf23c3b26d408716a2bfa892a9e6afdd", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5a18bba97c5bb88a9a9c8314c49db41e01997fac916cdc91112c5386ad9ba3f1", "generation_seconds_batch": 21.108391446061432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.085855484008789, "target_z": 4.687499849132358, "ce": 6.395919322967529, "genuineness": 4.545003414154053, "identity": 0.5916821956634521, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/096be7e73fd74737a8c0acd16911a6dccf23c3b26d408716a2bfa892a9e6afdd.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "09f62ed93e2be34a76bec63b28e5bb2e328456ad810c3939ac10ad14191b7064", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "455aa8079353b8b85c9f171bc1412813b3a1d66d09cdb896f54377423e1c262b", "generation_seconds_batch": 16.825003935955465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1479285955429077, "target_z": 2.4531249445339554, "ce": 6.3641486167907715, "genuineness": 4.306513786315918, "identity": 0.11166258156299591, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/09f62ed93e2be34a76bec63b28e5bb2e328456ad810c3939ac10ad14191b7064.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": "0a479afc12e267e5b7047c889506cd4e91dc587990652c41940c50b447975416", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ad51e2cbf3827ff107fb8591388842b204af3836ce4fab1b597d73ae6b499786", "generation_seconds_batch": 21.234317093039863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8234983682632446, "target_z": 4.062500008874567, "ce": 6.268836498260498, "genuineness": 4.6956281661987305, "identity": 0.6456077098846436, "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_Awe/0a479afc12e267e5b7047c889506cd4e91dc587990652c41940c50b447975416.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "0a581323473d2a4b3baf2cb15d47fa7cc51d103e8914637f481bf2fd88950eec", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2bb217fdbcbaf5bb2e49aba9ec5e68ac17ba5e3d5bf4c7b40633af9c0cd0b4bd", "generation_seconds_batch": 22.86908679001499, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6625678539276123, "target_z": 1.2968750554660446, "ce": 6.24500846862793, "genuineness": 4.394378662109375, "identity": 0.5988830327987671, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0a581323473d2a4b3baf2cb15d47fa7cc51d103e8914637f481bf2fd88950eec.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "0a611628095367df2d626f88655cffb6d5e2dc9035ae92b28874deda86e89942", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c0f7db2816fdc5483253c8777dc0da0659ea9db9a1cd0105b27d640af78e4104", "generation_seconds_batch": 24.19403005694039, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08866149187088013, "target_z": -0.07031250332796268, "ce": 6.133810997009277, "genuineness": 4.7332844734191895, "identity": 0.7449861168861389, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0a611628095367df2d626f88655cffb6d5e2dc9035ae92b28874deda86e89942.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "0a6fda7bde5d787ce1087096534cfb19e58b3ec8b52b37bbf9275fd3ee37d6e6", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "75be7e419df3862b9f903610398d30e3e73b775e02f40f3c33ea384ecb59de01", "generation_seconds_batch": 24.36152337503154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1938410997390747, "target_z": 2.5624999378780298, "ce": 6.09409761428833, "genuineness": 4.469690799713135, "identity": 0.67751544713974, "hypothesis": "J'ai trouvé la 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_Awe/0a6fda7bde5d787ce1087096534cfb19e58b3ec8b52b37bbf9275fd3ee37d6e6.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "0b2c56071a3d053ad081de1336fd2fd5e1f0cb8fee5b2dd79dda1f3f6e9133cd", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "210a720481da630cac0b4d6e8adcf003425aa10e976c2c19231a21fcfbffd8e1", "generation_seconds_batch": 21.563694206997752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35101866722106934, "target_z": 0.554687478922903, "ce": 6.292664527893066, "genuineness": 4.413206577301025, "identity": 0.4000697135925293, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0b2c56071a3d053ad081de1336fd2fd5e1f0cb8fee5b2dd79dda1f3f6e9133cd.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "0b31b472cd2926e70eb46e176f27c0c8f500dac61c2814a368a8092debf0a376", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ac4b384a0f3f348053d427cb1d008976e3e2266e27ea879f11d5c764c5e32e1c", "generation_seconds_batch": 23.469370484002866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8855714797973633, "target_z": 1.828125104276164, "ce": 6.292664527893066, "genuineness": 4.65797233581543, "identity": 0.6686012744903564, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0b31b472cd2926e70eb46e176f27c0c8f500dac61c2814a368a8092debf0a376.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "0b5cbef88d5fa528a0610758134df79a59dce2a9ca9247d342c73fc8df34c866", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "fc9fb3177b8260e0c1de9d17148c099d49eec8e511939e0eaeaac66ccc301e64", "generation_seconds_batch": 21.939476790023036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2960876524448395, "target_z": 0.4238281524556921, "ce": 6.252951145172119, "genuineness": 4.193545341491699, "identity": 0.19414696097373962, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0b5cbef88d5fa528a0610758134df79a59dce2a9ca9247d342c73fc8df34c866.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "0bcc0edf9bdfc08847c6fc2de6b1db6b92307aa3d2ecce4282b8cdd389c2db47", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1716ae85f017c1f314bbed47ab560b518192d659ca3dac1efbb330c18cc8fdff", "generation_seconds_batch": 26.961197689990513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2690320611000061, "target_z": 0.35937501109320896, "ce": 6.1020402908325195, "genuineness": 4.7081804275512695, "identity": 0.40531206130981445, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0bcc0edf9bdfc08847c6fc2de6b1db6b92307aa3d2ecce4282b8cdd389c2db47.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "0c9ee6e6b014006277d26dc6bab5af304a2f8c652e6969b1520e70c13191af8b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4453088f6ac453553d8130c749023561137ea114cfe469bf4cdd180f5c4617e", "generation_seconds_batch": 21.485125236096792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2069590091705322, "target_z": 2.5937500576846864, "ce": 5.959072113037109, "genuineness": 4.632867813110352, "identity": 0.8087947964668274, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vaix de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0c9ee6e6b014006277d26dc6bab5af304a2f8c652e6969b1520e70c13191af8b.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "0bed46ad0c0416d4c31a45ce57ddb24f98000a444f5e5a7850b74c0416454fc2", "generation_seconds_batch": 18.091744463075884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.036190055310726166, "target_z": -0.19531250332796268, "ce": 6.1894097328186035, "genuineness": 4.15588903427124, "identity": 0.4469458758831024, "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_Awe/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "0cbcd80ba871807c28baff07bc67e71d34df6e1ba2fa9052db01effc1de54d0f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "2fe68c434bf67f358da1011462863e426f0cfd44816efe1c07348402d1e28952", "generation_seconds_batch": 23.36708375706803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6332894563674927, "target_z": 3.609375117588015, "ce": 6.2767791748046875, "genuineness": 4.469690799713135, "identity": 0.5349324345588684, "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_Awe/0cbcd80ba871807c28baff07bc67e71d34df6e1ba2fa9052db01effc1de54d0f.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "0cc1d9231610a790ae53129bfd1c2f294baa76e1e0fe46e7a6c0186f7a37a28b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d9f22e98276036afa2c91af42a01915021bcb8e38170bc8a623da8a738601942", "generation_seconds_batch": 23.377871599048376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0364267826080322, "target_z": 2.1874999201288956, "ce": 6.1894097328186035, "genuineness": 4.632867813110352, "identity": 0.817665696144104, "hypothesis": "J'ai trouvé la 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_Awe/0cc1d9231610a790ae53129bfd1c2f294baa76e1e0fe46e7a6c0186f7a37a28b.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "0cf74d623368bdbb08f343f3c0f31993b45b207b8d1c5b3ef07a5c327172c523", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "9f9e2d2ed864258af0ca6aa1d20df446295889e580525648297435732b2d0552", "generation_seconds_batch": 25.187756229075603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.590419590473175, "target_z": 1.1249999645017315, "ce": 5.80021858215332, "genuineness": 4.65797233581543, "identity": 0.7574657201766968, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0cf74d623368bdbb08f343f3c0f31993b45b207b8d1c5b3ef07a5c327172c523.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "0d1aec9a302e87d2868df712dc0592d54c4ffd608adad282ba6c46a8370acfb2", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1d20fafe1de0e90dccf4e74d5adaef9dd2a430301e1d6c34a430e52b90999ca8", "generation_seconds_batch": 22.6599802140845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.440037727355957, "target_z": 5.531249960064448, "ce": 5.95112943649292, "genuineness": 4.432034492492676, "identity": 0.5784582495689392, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0d1aec9a302e87d2868df712dc0592d54c4ffd608adad282ba6c46a8370acfb2.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "0d411de5e477ff7fa17759cbd77142a27bb5e7ef80d1f7083a9b5bf1ead7fabc", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "faa7564b0ac34b8a1f430257a245a7bd9e1e5b94401ecfcd9a91f355bf56774d", "generation_seconds_batch": 23.213094190927222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4496394395828247, "target_z": 3.1718751442117163, "ce": 6.038498878479004, "genuineness": 4.582659721374512, "identity": 0.5266661643981934, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/0d411de5e477ff7fa17759cbd77142a27bb5e7ef80d1f7083a9b5bf1ead7fabc.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "0d4dca505afa3902133585acea78b8e0af069dae51bf69a410fa9c5398ac8007", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e51328441fed262a89a78ccc3d879b2cb53cf541fa3872c6c215769df32b86fc", "generation_seconds_batch": 21.066820133011788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.160809725522995, "target_z": 0.10156251663981342, "ce": 6.1020402908325195, "genuineness": 4.7332844734191895, "identity": 0.6898258924484253, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0d4dca505afa3902133585acea78b8e0af069dae51bf69a410fa9c5398ac8007.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "0d8e73f2ad46c2a9dcbd7b09c5ee04c01c7017ba14e393be002e6a9e435317ed", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "036bb9c8d0ef8f15ae468830b274c43e64ebc9ac55086fd6d35805c60a1d7a99", "generation_seconds_batch": 18.505269854911603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2263990044593811, "target_z": 0.2578124767042612, "ce": 6.133810997009277, "genuineness": 4.168440818786621, "identity": 0.5408869385719299, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0d8e73f2ad46c2a9dcbd7b09c5ee04c01c7017ba14e393be002e6a9e435317ed.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "0e064c21a76b63f173fb5fcb558dd0887a79b5502adb07835878c044610207ce", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b6da9397f5f3a377ecd644af2747c9c301f49c0f5e698d8bdadf859e27265ad8", "generation_seconds_batch": 21.0250612529926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9022055864334106, "target_z": 4.250000159742209, "ce": 6.213237762451172, "genuineness": 4.507347106933594, "identity": 0.35935109853744507, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0e064c21a76b63f173fb5fcb558dd0887a79b5502adb07835878c044610207ce.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "0e09bbd0a5254889f51fcc1e4db120719807ddefb3523332ba7c7086d9416c19", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6b0c72aa3387cd448196a99e3ecfa7a197aa4c902c831ca06e963eeb70aa1fbd", "generation_seconds_batch": 20.922795415041037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6986419558525085, "target_z": 1.382812529951664, "ce": 5.561938762664795, "genuineness": 4.306513786315918, "identity": 0.5058314800262451, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0e09bbd0a5254889f51fcc1e4db120719807ddefb3523332ba7c7086d9416c19.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "0e76882b352c20262c529e3c4097624e828e43fedd1a4a7e2e42ae402625278f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c158b11eb5cab84b6d655249e1b2524310b441e5ad006f253a02c86693536df8", "generation_seconds_batch": 21.0250612529926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.400684118270874, "target_z": 5.437499884630627, "ce": 6.324435234069824, "genuineness": 4.68307638168335, "identity": 0.39800170063972473, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0e76882b352c20262c529e3c4097624e828e43fedd1a4a7e2e42ae402625278f.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": "0e857693dfa1dabebf6d4c2c5e7a4994351ab49af4d29a646483430b1e2265f2", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6fe06cce3ef16546063e65e0c2ea3b6b9b0a11d472841f862c3dc9b1fd879550", "generation_seconds_batch": 17.200135480961762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21123149991035461, "target_z": 0.22167971204372477, "ce": 6.300607204437256, "genuineness": 4.362998008728027, "identity": 0.5303239822387695, "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_Awe/0e857693dfa1dabebf6d4c2c5e7a4994351ab49af4d29a646483430b1e2265f2.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "0eaa5dc44c89919da559eed6c29ab31d4217c782fa6e1a0df44b969d1661028b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e2d1946f045a0592f221982ba416db88551e6f7a2e9a11b08f93e2105a65f67d", "generation_seconds_batch": 24.01047313201707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9347634315490723, "target_z": 1.9453125565753655, "ce": 6.205295085906982, "genuineness": 4.595211505889893, "identity": 0.6836296319961548, "hypothesis": "J'ai trouvé la 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_Awe/0eaa5dc44c89919da559eed6c29ab31d4217c782fa6e1a0df44b969d1661028b.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "0eaa95f9bb4694e5b9730f9c56a700e02b05b1da4561d9764491bdbecbbf2a7e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "d07ef68e526952e081bc59b3f967f44a828279513c3475e57d389bba50d4fb92", "generation_seconds_batch": 28.007033691974357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2026228904724121, "target_z": 0.20117186529344216, "ce": 6.109982967376709, "genuineness": 4.68307638168335, "identity": 0.6792749166488647, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0eaa95f9bb4694e5b9730f9c56a700e02b05b1da4561d9764491bdbecbbf2a7e.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "0ed4c874e5204ef8ddee255e812c6652309a82b5dc2226fb9f6f4a05d6de25bc", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3ebb2ad54bb12ce131130717ea1f4ba623345301816973a625b4fc97cd4d7eed", "generation_seconds_batch": 17.641402338980697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8759697675704956, "target_z": 4.187499920128896, "ce": 6.23706579208374, "genuineness": 4.68307638168335, "identity": 0.49298790097236633, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0ed4c874e5204ef8ddee255e812c6652309a82b5dc2226fb9f6f4a05d6de25bc.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": "0ef30b914338eb9b3c6606ebf79ae5a54ea9231c724474607018fbed7c83f585", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7631427bd459b73fd77aca39d1a2d3a6d0785f192bee2060529a136fb5490ed6", "generation_seconds_batch": 18.228595850989223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0757803916931152, "target_z": 2.2812499955627166, "ce": 5.6413655281066895, "genuineness": 4.457139015197754, "identity": 0.7552740573883057, "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_Awe/0ef30b914338eb9b3c6606ebf79ae5a54ea9231c724474607018fbed7c83f585.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": "0f8f46b396a24d983f65c57ee9f98c98030dcd0e848349115d56b616adf587d6", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I wrote the number on the envelope.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "97fa89d6067b2f308c2ea9a8c337d5100cf9829f793fd8f711bdcd0986b9a971", "generation_seconds_batch": 24.462632821989246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3157644271850586, "target_z": 0.47070311917606533, "ce": 6.141753673553467, "genuineness": 4.074300289154053, "identity": 0.37101009488105774, "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_Awe/0f8f46b396a24d983f65c57ee9f98c98030dcd0e848349115d56b616adf587d6.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "0f9a2172b63008c617c589de90884161841060473c8bb7d37d67c7d5974fcfab", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "94e09be83830fe12282f857b746baf1089e0ba284b3a9dec69321ed7f3e3531b", "generation_seconds_batch": 23.87535902496893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6625678539276123, "target_z": 1.2968750554660446, "ce": 6.181467056274414, "genuineness": 4.6203155517578125, "identity": 0.6414965391159058, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0f9a2172b63008c617c589de90884161841060473c8bb7d37d67c7d5974fcfab.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "0fc565c7eea445d28a6d67cf64c67a8f4e8bee625488a556a8a9fc6b70c933bb", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "84d7e48eeb3a8deede4e00614445d3182229e4a8127ddd2f7f07f7a6eae228e4", "generation_seconds_batch": 24.393286861944944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0390595868229866, "target_z": -0.188476566243958, "ce": 6.268836498260498, "genuineness": 4.2751336097717285, "identity": 0.5209812521934509, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/0fc565c7eea445d28a6d67cf64c67a8f4e8bee625488a556a8a9fc6b70c933bb.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "103ea350a43f820c7a0323300b8cea9220f9e9211cdde07d72de62242818ecf2", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "371ed2cafb2fada075671dccf215d713cee7df41da698fccf9688a0a7f6b63a2", "generation_seconds_batch": 17.559982331003994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7478339672088623, "target_z": 1.50000012424394, "ce": 6.2767791748046875, "genuineness": 4.494794845581055, "identity": 0.6213375329971313, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/103ea350a43f820c7a0323300b8cea9220f9e9211cdde07d72de62242818ecf2.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "1057224a010736c64345a342513f8788ab37a0744ac03da83ed494e1fa0dab5a", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e1470947b4cf65cc4ed996b8ba79dd7db9a76886fdf725c95da88d9fb5eaa2f3", "generation_seconds_batch": 23.469037280068733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1599898487329483, "target_z": 0.09960936640276308, "ce": 6.09409761428833, "genuineness": 4.419482707977295, "identity": 0.06984049081802368, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/1057224a010736c64345a342513f8788ab37a0744ac03da83ed494e1fa0dab5a.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": "105ed7fd809afb8f76cd2c20db6f1833d2ee34642591d47e957a46d8ffe8e46b", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "28c639bd959d6f12c6a8925bb5ad9c89c881829a1450b19866c9e95f7def345c", "generation_seconds_batch": 23.316752639017068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18663549423217773, "target_z": 0.16308591489758678, "ce": 6.403861999511719, "genuineness": 4.293961524963379, "identity": 0.6357616186141968, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier, naast de hoge boekenkast. We zetten het na de lunch terug.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/105ed7fd809afb8f76cd2c20db6f1833d2ee34642591d47e957a46d8ffe8e46b.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": "1065324106d91cbc8ee9baea3b4c1e76fec9a6e037e4c41ba748084229549e14", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8dfec10a54467f22eaa99c99439953dcd11a12d0967be8eee3f40dbab36c7117", "generation_seconds_batch": 17.381291800993495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4920356571674347, "target_z": 0.8906249889067911, "ce": 6.38797664642334, "genuineness": 4.582659721374512, "identity": 0.53138267993927, "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_Awe/1065324106d91cbc8ee9baea3b4c1e76fec9a6e037e4c41ba748084229549e14.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "109f21251c2cb29b83a3bc98af6ca095818f8076ff2e2357c2da020c83159cb1", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "cbeb85fafc8d2b57d8dcb09dc7746383c5203307b80c78455d210bdba970fa9e", "generation_seconds_batch": 17.16063118900638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10054954886436462, "target_z": -0.04199219762255316, "ce": 6.340320587158203, "genuineness": 4.796044826507568, "identity": 0.6866223812103271, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/109f21251c2cb29b83a3bc98af6ca095818f8076ff2e2357c2da020c83159cb1.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "10dde85f6e539945a23bb69ea1410fad017b93467efeb8b1de6f9e8c97cf1daa", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3027f88bf90badccedb928f39d5167a7fb0195a4a2c904a395856448e34ec106", "generation_seconds_batch": 24.045497406972572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21000169217586517, "target_z": 0.21875000443728357, "ce": 6.141753673553467, "genuineness": 4.243753433227539, "identity": 0.44109195470809937, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/10dde85f6e539945a23bb69ea1410fad017b93467efeb8b1de6f9e8c97cf1daa.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": "111634363c9d4ca7db24c9fe8a622d683813a22cefdd00a6567b87d6d9ad505e", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6193524f241ad40a389b6ac8a0d3b128f1e2366fcf259f0a6acf4d9274aabf0d", "generation_seconds_batch": 15.5789674409898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1282519102096558, "target_z": 2.4062501908031937, "ce": 5.855817794799805, "genuineness": 4.105680465698242, "identity": 0.40966689586639404, "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_Awe/111634363c9d4ca7db24c9fe8a622d683813a22cefdd00a6567b87d6d9ad505e.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "116f6107719bfc482c8ddf3742a6cc43bec4de442b4ba8faeea391cab95b9cae", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "588a98cb14da8a3f94a3189b3b91793324ba35782d79d0d62e99b8c1b50e71f6", "generation_seconds_batch": 16.45134605304338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4037269353866577, "target_z": 3.0625001508676415, "ce": 6.38797664642334, "genuineness": 4.582659721374512, "identity": 0.3761715888977051, "hypothesis": "I've 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_Awe/116f6107719bfc482c8ddf3742a6cc43bec4de442b4ba8faeea391cab95b9cae.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "11a338a6b742b60ed50da9298b9558786e327734504f933b9bbc1c71dec4643b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "162117d0a0881f07dfa716ad7a911812b5cdce53ad4d57eecba2518ac2e90fdb", "generation_seconds_batch": 26.909323659958318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3329816162586212, "target_z": 0.5117187416800933, "ce": 6.205295085906982, "genuineness": 4.7081804275512695, "identity": 0.4597375988960266, "hypothesis": "Die Tür 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_Awe/11a338a6b742b60ed50da9298b9558786e327734504f933b9bbc1c71dec4643b.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "11c740a869a6fe8b3567bccf429137f2a2e22a67b94a6b6133634e4d94362b85", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "afa8d9981ab03f57e107a78196647ff0ab0181fbae2bc9676f86f876fbd9c231", "generation_seconds_batch": 23.496694679022767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3446965217590332, "target_z": 2.9218750377169105, "ce": 6.205295085906982, "genuineness": 4.65797233581543, "identity": 0.4823794364929199, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/11c740a869a6fe8b3567bccf429137f2a2e22a67b94a6b6133634e4d94362b85.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "11e1ac494d7c5b2317e4e6356b5eaf621f4771b76f39d1ad2edbd6cea5e0bd6d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2f7870e9f9c33fcaf4ad9d5089be2cebbb30d80da8c2596ec8c91911b88a578f", "generation_seconds_batch": 24.03220355103258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.852776825428009, "target_z": 1.7500000887456715, "ce": 6.141753673553467, "genuineness": 4.457139015197754, "identity": 0.3579411208629608, "hypothesis": "The door is s still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/11e1ac494d7c5b2317e4e6356b5eaf621f4771b76f39d1ad2edbd6cea5e0bd6d.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "12143c1eb53baf8c088e7d548dd50b07f121e4bbb3bcb8c14a5d3f11062afdd3", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3ca00ac8d6831d135b46dcf7ffdabe87f790d880121f7dbcea275fd2338d84ce", "generation_seconds_batch": 24.091228040051647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7316733598709106, "target_z": 3.843750022186418, "ce": 5.8875885009765625, "genuineness": 4.557555198669434, "identity": 0.5733407735824585, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/12143c1eb53baf8c088e7d548dd50b07f121e4bbb3bcb8c14a5d3f11062afdd3.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "123a3d362d4b03faece47426f943d42c1e0dbe587b21a709294bfcb008c02d15", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "11544118ba31ca5b899eb83cd2b0364fb76de06c84f406d354a49dd09eca2385", "generation_seconds_batch": 24.047943711979315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16367924213409424, "target_z": 0.10839841822554946, "ce": 6.213237762451172, "genuineness": 4.758388519287109, "identity": 0.49922311305999756, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/123a3d362d4b03faece47426f943d42c1e0dbe587b21a709294bfcb008c02d15.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "1240592b110bd565a2790c265402f4836f1cee94114d5cf59eba7c3b47f24189", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "bc8eb0d9f52a1deacd0682d89f0a59c00e0d79ed18cb43d84279344b90f49c1b", "generation_seconds_batch": 28.773778139962815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2477155327796936, "target_z": 0.30859374389873506, "ce": 6.197352409362793, "genuineness": 4.356721878051758, "identity": 0.7082138061523438, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/1240592b110bd565a2790c265402f4836f1cee94114d5cf59eba7c3b47f24189.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "12514c5281c81cd9eaed4d379996e5875467503a4a3825395e541f646726cec1", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "667cbfca2d5e7255d2e21f33d7aef40ba67c42dc5c34ab9c9ad9c7ddbfb2dc5a", "generation_seconds_batch": 24.388069521053694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2444360852241516, "target_z": 0.3007812849436082, "ce": 6.2767791748046875, "genuineness": 4.482243061065674, "identity": 0.5969663858413696, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/12514c5281c81cd9eaed4d379996e5875467503a4a3825395e541f646726cec1.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "126fa153216c3443181f94c2aa99fa02f086a72fb6314e01006756395816be2a", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "41560460773cf634262530af1fac23314093cfad4cda1ec3fdbaec3e6d111b68", "generation_seconds_batch": 23.817916917963885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3575775921344757, "target_z": 0.570312467829694, "ce": 6.292664527893066, "genuineness": 4.118232727050781, "identity": 0.2047010362148285, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/126fa153216c3443181f94c2aa99fa02f086a72fb6314e01006756395816be2a.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "127cc5dbd8a35b032b348b9c738a2eb5e5ae7bb28fdaf095fc1b982833693ffc", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "5ca454c4237434211e57cf204978140a05acd7ed4b871308d727cf79a2ac9149", "generation_seconds_batch": 24.78261285298504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2755909860134125, "target_z": 0.375, "ce": 6.340320587158203, "genuineness": 4.7081804275512695, "identity": 0.5682631731033325, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/127cc5dbd8a35b032b348b9c738a2eb5e5ae7bb28fdaf095fc1b982833693ffc.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "65b952ca8ac7d131a36e510cb2ca05042d6f7a5f422e5995fdc5aa07154999ac", "generation_seconds_batch": 17.878399697947316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20877188444137573, "target_z": 0.21582029683084236, "ce": 6.006728172302246, "genuineness": 4.557555198669434, "identity": 0.7434880137443542, "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_Awe/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "12b5ebfbbd35fd57d4e39d9c09eeb0fe72dc85ebbdb54d1d8efc3f329c61038b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9885334826c87908ea87d023eea1cfd4ca5c0c91bc717797561f0cadad777a13", "generation_seconds_batch": 24.09472017304506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5182713866233826, "target_z": 0.9531250155304926, "ce": 6.348263263702393, "genuineness": 4.7458367347717285, "identity": 0.4370902180671692, "hypothesis": "Die Tür 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_Awe/12b5ebfbbd35fd57d4e39d9c09eeb0fe72dc85ebbdb54d1d8efc3f329c61038b.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "12dbe95ef4fbbc89cf675b99ef747c1046e8463f462015cd02e603b1bacd71de", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6a9921a75863d6b887963c4aefbda58887e715cd312179e2827fd28ee4a0b7b0", "generation_seconds_batch": 24.75342698104214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1479285955429077, "target_z": 2.4531249445339554, "ce": 6.24500846862793, "genuineness": 4.494794845581055, "identity": 0.5069829225540161, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/12dbe95ef4fbbc89cf675b99ef747c1046e8463f462015cd02e603b1bacd71de.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "143df92e5be673c4285b38b45d1e439f03670fab9407cab5b78935cce05a55c4", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e30abf88d434e5df8ecdbf9a2400c885a14d9f3b7954540d151332c352f08b1d", "generation_seconds_batch": 17.890956277027726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2463126182556152, "target_z": 2.6875001331185073, "ce": 6.221180438995361, "genuineness": 4.607763767242432, "identity": 0.6569938063621521, "hypothesis": "J'ai trouvé la 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_Awe/143df92e5be673c4285b38b45d1e439f03670fab9407cab5b78935cce05a55c4.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "144834ebae477c3e3901aec7509fa17c44a7e4755319ca7c3232588f410c8863", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4ffff6efd476524ec11e5ff187e9d151b71ab62fae7ab7b3e506f53b6bf583be", "generation_seconds_batch": 24.06023435399402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6855241060256958, "target_z": 1.351562552138082, "ce": 6.181467056274414, "genuineness": 4.720732688903809, "identity": 0.8242759108543396, "hypothesis": "J'ai trouvé la 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_Awe/144834ebae477c3e3901aec7509fa17c44a7e4755319ca7c3232588f410c8863.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": "148d8ddbda4f902c6b1711cb8c5382e1e1edbd9effbaf68628c1983174e0789e", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "25556e4640aa71cade9012dda0ecd1c30c170082732ffa531cf1da9b90e90323", "generation_seconds_batch": 21.234317093039863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9940305948257446, "target_z": 4.468750146430358, "ce": 5.974957466125488, "genuineness": 4.582659721374512, "identity": 0.3908069133758545, "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_Awe/148d8ddbda4f902c6b1711cb8c5382e1e1edbd9effbaf68628c1983174e0789e.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "1534ab3e55c926d9191eea2615197a51880a3952f70fbb6c3e7052adfb035347", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "97b06a743c80c1a5065ae9bb3d9123f8a67966109acbdec2aea141739472ede1", "generation_seconds_batch": 17.437000641948543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2856661081314087, "target_z": 2.781249924566179, "ce": 5.661221981048584, "genuineness": 4.300237655639648, "identity": 0.4395796060562134, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/1534ab3e55c926d9191eea2615197a51880a3952f70fbb6c3e7052adfb035347.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "153fa40dcfd7865aa3df0d47fe3fcd9d140f48c0ce4fa8e2fa71ce9cc13a8889", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "1e1bde4ede84cbdb8ae80f683f409f44f088430d3858798a31dda7588d6ff81c", "generation_seconds_batch": 23.30994353699498, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5379481911659241, "target_z": 1.000000053247403, "ce": 6.260893821716309, "genuineness": 4.65797233581543, "identity": 0.5451557040214539, "hypothesis": "Die Tür 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_Awe/153fa40dcfd7865aa3df0d47fe3fcd9d140f48c0ce4fa8e2fa71ce9cc13a8889.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "d37414e714e4e9dfa0ab26101202e3d858608c35bc0a6d631413049897962df6", "generation_seconds_batch": 16.32373954798095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2120513617992401, "target_z": 0.2236328267825065, "ce": 6.348263263702393, "genuineness": 4.256305694580078, "identity": 0.549798846244812, "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_Awe/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "15b57851509e9900a23aeced20b65d048d55b67fc9604bf8f3b00c29cb8f9e82", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fd4f1de6c9f3d538d0786a7921871a4a314e2da61e3af68403abe0a689fbf6d1", "generation_seconds_batch": 24.13139084202703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2594304084777832, "target_z": 2.718749968939015, "ce": 5.831989288330078, "genuineness": 4.65797233581543, "identity": 0.5422119498252869, "hypothesis": "Encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/15b57851509e9900a23aeced20b65d048d55b67fc9604bf8f3b00c29cb8f9e82.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "15c8ed25d1aca2f73ce162dc66e338025c61183fca521c97767beb8b1da44cb4", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "05c31c6b0d16db6be90679093e753d5ab0cb8d2f28cd3fb93d68356a3111aea0", "generation_seconds_batch": 17.16063118900638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04561851918697357, "target_z": -0.17285155958803267, "ce": 6.125868320465088, "genuineness": 4.469690799713135, "identity": 0.4930068254470825, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/15c8ed25d1aca2f73ce162dc66e338025c61183fca521c97767beb8b1da44cb4.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "16831ae8bc1a8af5c60ebd1a18a039ccf2e1d707519edfaecc98facf4fcb0e8d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "14fb907fe36afd1d0d7c4d62c455f7054f9213083ab75579f2754138c905741b", "generation_seconds_batch": 24.213599503040314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7314366102218628, "target_z": 1.4609375454821567, "ce": 6.348263263702393, "genuineness": 4.406930446624756, "identity": 0.641588568687439, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/16831ae8bc1a8af5c60ebd1a18a039ccf2e1d707519edfaecc98facf4fcb0e8d.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "172495066df2deaab8d0e33c0d021812f2f238dbf91c30fc8de3503e53922156", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "133ae55f6cf78204e9c677c3c1c3c2927328a8931e66d22fe8edabe0a8d91f12", "generation_seconds_batch": 25.43686308595352, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8298205733299255, "target_z": 1.6953125920736343, "ce": 6.23706579208374, "genuineness": 4.532451152801514, "identity": 0.6018104553222656, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/172495066df2deaab8d0e33c0d021812f2f238dbf91c30fc8de3503e53922156.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "1753249157c16fa5aba37c28c02b410c5a6b1831766791b3263fdbc8c9d72e0e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "96b614327eb3450076b311a0d90a443cb8edc86e6a5b7ff24da7bd94d59df94f", "generation_seconds_batch": 17.9412726869341, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32806241512298584, "target_z": 0.49999998225086567, "ce": 6.268836498260498, "genuineness": 4.65797233581543, "identity": 0.5321646332740784, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/1753249157c16fa5aba37c28c02b410c5a6b1831766791b3263fdbc8c9d72e0e.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "190a7098966fbd435906ae9989afdd603806abf4e640ef96bc17a7324036435b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "fdea2b650470b0eb0348b554bd032446328cdc08daae221957d3ae4bfa354428", "generation_seconds_batch": 22.76199042191729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24361619353294373, "target_z": 0.29882809920828923, "ce": 6.221180438995361, "genuineness": 3.8797430992126465, "identity": 0.2757079303264618, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/190a7098966fbd435906ae9989afdd603806abf4e640ef96bc17a7324036435b.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "191cbbb96ec8e5b3351aab1019ce24b70e51372669f86e87b1dcedff14456158", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6151ea58b50188050f91f71eeefa90b62f424d9a7a23f492b83448529988bf4c", "generation_seconds_batch": 26.76430962199811, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.129244863986969, "target_z": 0.02636717321749349, "ce": 6.1020402908325195, "genuineness": 4.607763767242432, "identity": 0.7153547406196594, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/191cbbb96ec8e5b3351aab1019ce24b70e51372669f86e87b1dcedff14456158.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "1930e5c430bebc2d5e8af017b9907c29d53bc980c2f26d1ed513fa577d3a198f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "10047ceaf767f1094b69a4416f2f6abe41c39b68e230071ea3d99f4c2b4a2977", "generation_seconds_batch": 17.548447089036927, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4657999277114868, "target_z": 0.8281249622830896, "ce": 6.3641486167907715, "genuineness": 4.356721878051758, "identity": 0.4703003764152527, "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_Awe/1930e5c430bebc2d5e8af017b9907c29d53bc980c2f26d1ed513fa577d3a198f.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "198c4da3e00e65d25e9bb6916bea96b062ad172d8ec2e9585d9ff98686ed1293", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "b602e6a08fe2ac64e496ca095b709fd515838a907e7970059a3ee4d30f669760", "generation_seconds_batch": 20.0765842969995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1923745572566986, "target_z": 0.1767577890655961, "ce": 6.213237762451172, "genuineness": 4.65797233581543, "identity": 0.48195648193359375, "hypothesis": "Die Tür 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_Awe/198c4da3e00e65d25e9bb6916bea96b062ad172d8ec2e9585d9ff98686ed1293.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": "19f622120a6c054f08bfcc09266fae0fc5c0775f189a334ac358baf9f82f18a5", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "ca28f44e8b7b4561a6c95142991e3a857530e058f740e90d9821a5db71184952", "generation_seconds_batch": 23.27120200707577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2723115086555481, "target_z": 0.36718747004833585, "ce": 5.982900142669678, "genuineness": 4.65797233581543, "identity": 0.4994491934776306, "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": 0.120000000000001, "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_Awe/19f622120a6c054f08bfcc09266fae0fc5c0775f189a334ac358baf9f82f18a5.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "1a18d028eaba4d75e7c0b48946fa5ff55f8f12c0f53f97523564a968cbc5985d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "49ca80d6b7bfceea2e1b66ae70df845642bb2e5c4d21a41ebc9c4663c8fe866c", "generation_seconds_batch": 17.41929367906414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7084803581237793, "target_z": 1.4062500488101193, "ce": 6.4515180587768555, "genuineness": 4.20609712600708, "identity": 0.6019984483718872, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/1a18d028eaba4d75e7c0b48946fa5ff55f8f12c0f53f97523564a968cbc5985d.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "1a367d8e216682efb2f4beb6f8e4ef775e51f0f262ae092c396c6d85d29d7b74", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "56f1ddd5bac71c1380b4f997168a968786d5270517ffc29148356f6555dc4c65", "generation_seconds_batch": 17.391618467052467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8396589756011963, "target_z": 1.7187501109320893, "ce": 6.459460258483887, "genuineness": 4.457139015197754, "identity": 0.5476553440093994, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/1a367d8e216682efb2f4beb6f8e4ef775e51f0f262ae092c396c6d85d29d7b74.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "1a4728c23d0a87e4a3067b44deb38a7706d9fb8057597b2193c37fbddee6964d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1ab947b90e08e370efad94f2e5d784b8f4c8bb11a353a5a39f10c0447770c9fe", "generation_seconds_batch": 23.99432227399666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.348212718963623, "target_z": 5.3124999733762985, "ce": 6.308549880981445, "genuineness": 4.557555198669434, "identity": 0.33168405294418335, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/1a4728c23d0a87e4a3067b44deb38a7706d9fb8057597b2193c37fbddee6964d.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": "1aa95773a7e079444b9682b98900191314f1d039b2ee3f7fe895620dc75cb5ea", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I wrote the number on the envelope.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "42bb32638518c985ff23887e586077dd14910b971eb99457745d9c55b667afbc", "generation_seconds_batch": 17.154403944965452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21943014860153198, "target_z": 0.2412109304280793, "ce": 6.300607204437256, "genuineness": 4.18099308013916, "identity": 0.5225738286972046, "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_Awe/1aa95773a7e079444b9682b98900191314f1d039b2ee3f7fe895620dc75cb5ea.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "1afc0476b3e08330a048b03df61b20dfb8dea772f749f3d315bf3cbe539f5332", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "fc5e157b20e6776de478c43fd595573ad851baab4eed1344d6672565eba4fdbd", "generation_seconds_batch": 23.90323074697517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22065994143486023, "target_z": 0.2441406025362519, "ce": 6.109982967376709, "genuineness": 4.293961524963379, "identity": 0.6633409857749939, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/1afc0476b3e08330a048b03df61b20dfb8dea772f749f3d315bf3cbe539f5332.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "1b00244d7cab9148712fad8e44247fc9bf8f548af55391b4697c752194c73330", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e08faf26797b75294193e3d3e12948669bf010f1674a97ba0d00fb2b3f38cd73", "generation_seconds_batch": 23.892318962025456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13908326625823975, "target_z": 0.04980469207594869, "ce": 6.078212261199951, "genuineness": 4.65797233581543, "identity": 0.6937214136123657, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/1b00244d7cab9148712fad8e44247fc9bf8f548af55391b4697c752194c73330.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "1b24d02402858cd1090a1f0c66b4d2dd626bc1d7c20f817cbfcd5d80a61b0377", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0206d39a6cd39710e6e41a1236b44bfa6886b94e586d5fd4d666331e34d86ab3", "generation_seconds_batch": 23.741508404025808, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27723070979118347, "target_z": 0.37890622947756347, "ce": 6.221180438995361, "genuineness": 4.532451152801514, "identity": 0.6064047813415527, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/1b24d02402858cd1090a1f0c66b4d2dd626bc1d7c20f817cbfcd5d80a61b0377.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "1b2e412674dd40ad5b68f9c5c6729cf8e8d39052c1019f030973d095bcf7e0a1", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ad4e9cedc2b24302adb8f778ba087d4c12a02d8a160e66ed3df921c8ee9afe23", "generation_seconds_batch": 25.438535648048855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0620158426463604, "target_z": -0.13378906069735355, "ce": 6.141753673553467, "genuineness": 4.344170093536377, "identity": 0.7291357517242432, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/1b2e412674dd40ad5b68f9c5c6729cf8e8d39052c1019f030973d095bcf7e0a1.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": "1c564cd2c7ee87c335ad68c122aa03389c2bff86ac90eef18a16e25d590bc0de", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3d2187b34ecb6ed6f874d46da50465236388e698c7c49f8663a24e74381bd8a7", "generation_seconds_batch": 23.014687333954498, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2263990044593811, "target_z": 0.2578124767042612, "ce": 5.756534099578857, "genuineness": 4.570107460021973, "identity": 0.8201284408569336, "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_Awe/1c564cd2c7ee87c335ad68c122aa03389c2bff86ac90eef18a16e25d590bc0de.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "1c57cc79e62c20d84daa496e107bf0f74072c774f533936d356a23f0dacb1aec", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "db06f15b32789ed4c5fbfe0a5b6ef3662219a3d455f8e57e7a07d8f4f676c482", "generation_seconds_batch": 15.402962386026047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.675685703754425, "target_z": 1.3281250332796268, "ce": 6.229123115539551, "genuineness": 4.532451152801514, "identity": 0.585605263710022, "hypothesis": "J'ai trouvé la 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_Awe/1c57cc79e62c20d84daa496e107bf0f74072c774f533936d356a23f0dacb1aec.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "1cd682e42ab08d750deaa079727c5ae7871dda025222e69458566deea3d338c4", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0f86db62538edea78ea5aa2da64221a9fbaf1d5a78a685e1795af1baaf81fdb5", "generation_seconds_batch": 23.377871599048376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8724535703659058, "target_z": 1.7968749844695076, "ce": 6.205295085906982, "genuineness": 4.645420074462891, "identity": 0.7077777981758118, "hypothesis": "J'ai trouvé la 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_Awe/1cd682e42ab08d750deaa079727c5ae7871dda025222e69458566deea3d338c4.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "1ce622686b1f849d348704412842d611d91029f41debf8cfe7145f6b546186c2", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "a8eb6440e2e2b4a71c2a59bbd3593a14f4fd0cecea93d589a648a1a288ad8c5d", "generation_seconds_batch": 25.556785881053656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1938410997390747, "target_z": 2.5624999378780298, "ce": 6.55477237701416, "genuineness": 4.582659721374512, "identity": 0.6470365524291992, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/1ce622686b1f849d348704412842d611d91029f41debf8cfe7145f6b546186c2.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "1d13b106d4676dc31171f8217832d5180127d9c464479cb2993f4432389136be", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b46e811af248ef8c3a33b97f2703e82210fd9d42ed84272e49aa9bd326cfad11", "generation_seconds_batch": 21.94421207997948, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.112091302871704, "target_z": 4.750000088745671, "ce": 5.7128496170043945, "genuineness": 4.425758361816406, "identity": 0.43761682510375977, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/1d13b106d4676dc31171f8217832d5180127d9c464479cb2993f4432389136be.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "c7c56efd191e3d5d08da4b8cdc632a17ea3c99f18c6fda162a4c6d6d02b36224", "generation_seconds_batch": 17.826077078003436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23541754484176636, "target_z": 0.27929688082393467, "ce": 6.41180419921875, "genuineness": 4.268857479095459, "identity": 0.5120747089385986, "hypothesis": "Escribí el número en el sobre, le lo viene y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "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_Awe/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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "f8c36d8babe0365f59c79b4134130d48ae4887b766a9b95602c1341fcffabdd5", "generation_seconds_batch": 16.575160778011195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08005289733409882, "target_z": -0.09082031457997668, "ce": 6.316492557525635, "genuineness": 4.532451152801514, "identity": 0.6039507389068604, "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_Awe/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "1db7dcb9aa1b6354cf511b607e78872050ad17376eb3ee5368d70352b99dbda9", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "74b5fb693c37e0c98206ddceda27b1ed5609f36fbf969bc2f6be08d67c5dc439", "generation_seconds_batch": 23.14142889797222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5086697340011597, "target_z": 3.3124999733762985, "ce": 6.332377910614014, "genuineness": 4.482243061065674, "identity": 0.5374637842178345, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/1db7dcb9aa1b6354cf511b607e78872050ad17376eb3ee5368d70352b99dbda9.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "1dc3e4ae0088158e618e27c121f2c2c3fe471dd1877f1b82a619a49d2dbeed48", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "432b2cf7047d02aa951bf43d1d1bb035a4658fa66936f9ad113e02ddd8469a58", "generation_seconds_batch": 21.479282796033658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12432567030191422, "target_z": 0.014648431537400195, "ce": 6.2767791748046875, "genuineness": 4.68307638168335, "identity": 0.5803351998329163, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/1dc3e4ae0088158e618e27c121f2c2c3fe471dd1877f1b82a619a49d2dbeed48.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": "1ddfa1e879fc4f1317795641af94c61c5a0c79473cef2c668dc25474959b6165", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a5119efa98db22433671d8b1dc52a21075cb57aad57d9eb16e6e8b9f647dc1af", "generation_seconds_batch": 15.657913833972998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32478296756744385, "target_z": 0.4921875232957388, "ce": 6.038498878479004, "genuineness": 4.6956281661987305, "identity": 0.7249579429626465, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis peu près de la fenêtre. Prends les quand tu partiras.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/1ddfa1e879fc4f1317795641af94c61c5a0c79473cef2c668dc25474959b6165.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": "1e0ffb1bc5dff1e14cca683936b6871f07549666863222dcab891d6acbdee24f", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The road turns left behind the bridge.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "677765d7efe05a30249721a5eed4b7f576a7ba14c6fd261fe4950e1b649b7300", "generation_seconds_batch": 22.908827190985903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1413697004318237, "target_z": 2.4375000266237015, "ce": 6.316492557525635, "genuineness": 4.432034492492676, "identity": 0.4081624746322632, "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_Awe/1e0ffb1bc5dff1e14cca683936b6871f07549666863222dcab891d6acbdee24f.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "1e33b89e438618eaca3c21d9c85d943da531733f0fdd29c686c244d8066fa587", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "61098ac9a997f03c29ae00ffac36e2fc718e6ee762e530ae1af0b2d12c895a95", "generation_seconds_batch": 22.382551705930382, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7478339672088623, "target_z": 1.50000012424394, "ce": 6.213237762451172, "genuineness": 4.444586753845215, "identity": 0.5806860327720642, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het Oude Raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/1e33b89e438618eaca3c21d9c85d943da531733f0fdd29c686c244d8066fa587.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "010657bdc04b58aba625ad050fd6ad83c86fad9d3bdf2f23a2d22b6f88950c40", "generation_seconds_batch": 17.826077078003436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.138673335313797, "target_z": 0.04882813470655782, "ce": 6.316492557525635, "genuineness": 4.356721878051758, "identity": 0.664743185043335, "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_Awe/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "1f4ef40e3dc9ef86adc262f138ba032a94a697e4d22cedbd2ee206475a75ef29", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "83d99867515210adf4c6dcd44bb9ef3685bbae764e5e508041b4d5593d1324eb", "generation_seconds_batch": 23.94108139409218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9677948951721191, "target_z": 4.406250190803194, "ce": 6.356205940246582, "genuineness": 4.545003414154053, "identity": 0.33767423033714294, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/1f4ef40e3dc9ef86adc262f138ba032a94a697e4d22cedbd2ee206475a75ef29.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "1f676112bc451169582f3f3f5654996e00600c4711311851eb798edefb882c91", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "26c5d92d4bd034d25deeb3b34948e36c564c349ae4ec426298dfb5ab0708e9ec", "generation_seconds_batch": 17.68239559500944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07923303544521332, "target_z": -0.09277342931875841, "ce": 6.046441555023193, "genuineness": 4.7332844734191895, "identity": 0.4488828778266907, "hypothesis": "Die Tür 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_Awe/1f676112bc451169582f3f3f5654996e00600c4711311851eb798edefb882c91.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "1fc8b8e87182ba7d11a363f72bdb9b7196efa03249d236ccbb219b3e0d205d2f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "061d6220a587b26a184abfa9e4cc6f0fd080541adfab0b8fe152fccca1d6f04b", "generation_seconds_batch": 27.550500173005275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4428436756134033, "target_z": 0.7734374656110523, "ce": 6.332377910614014, "genuineness": 4.846253395080566, "identity": 0.4289211630821228, "hypothesis": "Die Tür 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_Awe/1fc8b8e87182ba7d11a363f72bdb9b7196efa03249d236ccbb219b3e0d205d2f.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "1feb5ca516c25c9f7b751566d864b493e858e9d98fe3d7b7def438a37c89578f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f4878f7fd671981c464b3e61ebe2d1b87e9f6c0cbb5779f244b26f6b2d4c8df5", "generation_seconds_batch": 23.872623622999527, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12391573935747147, "target_z": 0.01367187416800933, "ce": 6.316492557525635, "genuineness": 4.507347106933594, "identity": 0.5884625315666199, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/1feb5ca516c25c9f7b751566d864b493e858e9d98fe3d7b7def438a37c89578f.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": "204eeb59f3ab1aa6dbfd0ac7cbd1c4731a05c8afa18374052a1224363984f4b4", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d9be885fd153b8f18d012abb35866f3cda61f2d20ccd2c076bf2863709ec9ff5", "generation_seconds_batch": 17.432622501975857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0036321878433228, "target_z": 2.1093750465914773, "ce": 5.764476776123047, "genuineness": 4.432034492492676, "identity": 0.5172713398933411, "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_Awe/204eeb59f3ab1aa6dbfd0ac7cbd1c4731a05c8afa18374052a1224363984f4b4.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "2084abca93c60295efe68f6e9101e777abb59be61d8c03a86d9ab5e6453f0575", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b544b9e54ce55036e7543191e3898dd6ece11d028118cb96a2f562a0e91eb97d", "generation_seconds_batch": 24.113063510973006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4627572298049927, "target_z": 3.203124980032224, "ce": 6.419747352600098, "genuineness": 4.262581825256348, "identity": 0.344113290309906, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/2084abca93c60295efe68f6e9101e777abb59be61d8c03a86d9ab5e6453f0575.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": "21292d67d20bdf86df06c69c088bd5d310dd8aaf6237422eb75914072ce00d40", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7a38bc9ccac9487df7eb4e1d3663dd299a214277f8b81ad006f9f0a5837d489d", "generation_seconds_batch": 18.518495627096854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8626152276992798, "target_z": 1.7734376076041267, "ce": 6.1020402908325195, "genuineness": 4.833701133728027, "identity": 0.8526884913444519, "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_Awe/21292d67d20bdf86df06c69c088bd5d310dd8aaf6237422eb75914072ce00d40.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "225a6fc7553f6bb78ba9ac4a94263eedf0fcd339a6c56e3ccfb4e5bd97b7ea2b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "83550cf5710f454d075b523d9e23cb1287b4e09a2b9b3b216fd453848eecf776", "generation_seconds_batch": 22.819348535966128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7281571626663208, "target_z": 1.4531250865270298, "ce": 5.998785495758057, "genuineness": 4.557555198669434, "identity": 0.6507031321525574, "hypothesis": "J'ai trouvé la 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_Awe/225a6fc7553f6bb78ba9ac4a94263eedf0fcd339a6c56e3ccfb4e5bd97b7ea2b.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": "225f498f5fd4e2fb0be066932282f64186262eacdfb5a161ce9d721b2ec41b75", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8181ad4ed4902b67b09aaf8977b486892e6d2be9157cdc3c6f4feec344bd8e9f", "generation_seconds_batch": 23.529091028962284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4234037399291992, "target_z": 3.109375188584552, "ce": 5.808161735534668, "genuineness": 3.898571252822876, "identity": 0.5009207129478455, "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_Awe/225f498f5fd4e2fb0be066932282f64186262eacdfb5a161ce9d721b2ec41b75.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": "231a42291e48d1d670c53da59a37ef94449f06ef6298c2940c0d2948ccea1038", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5580f56340b2718d3fdd636076f5e5642350c25324bd64fb7f92c1c3b02a8b8d", "generation_seconds_batch": 23.2968109321082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1741644144058228, "target_z": 2.5156251841472685, "ce": 5.6254801750183105, "genuineness": 4.080576419830322, "identity": 0.3549836277961731, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/231a42291e48d1d670c53da59a37ef94449f06ef6298c2940c0d2948ccea1038.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "238e4272484eadaccd218df8589b3a5b7d8aa153cddf1e94fb8580348cf824e0", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "78955afbd048325b5872366fcaca9e59d4fe051bda62edfe09476bff5921915c", "generation_seconds_batch": 23.292711919988506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15794017910957336, "target_z": 0.09472654405754014, "ce": 6.157639026641846, "genuineness": 4.362998008728027, "identity": 0.621885359287262, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/238e4272484eadaccd218df8589b3a5b7d8aa153cddf1e94fb8580348cf824e0.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "2392577cb8f9236a054e18f71bcbc86616a280bee33ed3b8bb39211ed17adb73", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cd38c307f86b0e4bae87f11c7f7a4a9570f94cfedbe8b0eaa679b2cc483473c2", "generation_seconds_batch": 24.190890930010937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6691268086433411, "target_z": 1.312500115369373, "ce": 6.1894097328186035, "genuineness": 4.595211505889893, "identity": 0.40779411792755127, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/2392577cb8f9236a054e18f71bcbc86616a280bee33ed3b8bb39211ed17adb73.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "2533181e8110e0c7b6eff4071d74b4a3002d228d8f785fd010ef2f51da7d2082", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "047e622494586f9cb3f301ce6d8a5694e0f76820e2d761ca1709e158e86b9738", "generation_seconds_batch": 26.578823543037288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5021108388900757, "target_z": 3.2968750554660446, "ce": 6.221180438995361, "genuineness": 4.632867813110352, "identity": 0.673406720161438, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/2533181e8110e0c7b6eff4071d74b4a3002d228d8f785fd010ef2f51da7d2082.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "2576553204884dce45747da44f0255bd5c7f08b732a000853c9ab3fe67159912", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ac1b0a49d1cfd3d77850d0b64c62791db015109b53cff181b78851f354170ccd", "generation_seconds_batch": 24.584344813018106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.007148265838623, "target_z": 4.499999698264717, "ce": 6.300607204437256, "genuineness": 4.65797233581543, "identity": 0.5454487204551697, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/2576553204884dce45747da44f0255bd5c7f08b732a000853c9ab3fe67159912.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": "25845c49d53ea548ae880530a4632d73a0165796a139530153afcb0bfa6fd819", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "538ae53e7f60f43a82015de3e6cc371b44cf027d41ddbfc03bbc17e0aefbbf7c", "generation_seconds_batch": 15.539111061953008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4365215301513672, "target_z": 3.1406250244050598, "ce": 6.125868320465088, "genuineness": 4.482243061065674, "identity": 0.5000172257423401, "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_Awe/25845c49d53ea548ae880530a4632d73a0165796a139530153afcb0bfa6fd819.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": "25934f391bb4006ced438bc3f632a192ea58e076a53a7f94e55d8b752ec5e8ba", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Someone moved the little blue chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c828bc2ad72b0d1286ff804df9f4666b2f6972c6e022a2a4b50cca1ab49ead5c", "generation_seconds_batch": 25.272634807042778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8265410661697388, "target_z": 1.687499991125433, "ce": 6.38797664642334, "genuineness": 4.432034492492676, "identity": 0.3803563416004181, "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_Awe/25934f391bb4006ced438bc3f632a192ea58e076a53a7f94e55d8b752ec5e8ba.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "25d524ff23758af135e62fb3176fea3a9991453273772a4ddae101b6469b4bd6", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "77ae4579e06edf90c2a36f98207f6f6716f4fc810900c3625e065dff2d9e1c51", "generation_seconds_batch": 18.852255712030455, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4627572298049927, "target_z": 3.203124980032224, "ce": 5.959072113037109, "genuineness": 4.381826400756836, "identity": 0.4236885905265808, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/25d524ff23758af135e62fb3176fea3a9991453273772a4ddae101b6469b4bd6.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "25e77a3c6a1d35b300173ebddd0545e5e552df48b84d166931eb450279d8c775", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "91be3137fb00bdd567e7fe243686967f4e46d0afde6a80e6dd5b8dd064d88ee8", "generation_seconds_batch": 23.902794518042356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14687199890613556, "target_z": 0.06835938858918095, "ce": 6.292664527893066, "genuineness": 4.519899368286133, "identity": 0.4140099883079529, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/25e77a3c6a1d35b300173ebddd0545e5e552df48b84d166931eb450279d8c775.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "25efd1273663b69648ed99af67248aa998af2495497cae8d34907bfbb58193e4", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e4a9e60d93f0f94b276e042392ad0d6d20cd1f5d8fff8172ea5d636b88693f1f", "generation_seconds_batch": 17.733103750040755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0167499780654907, "target_z": 2.140624882411985, "ce": 6.157639026641846, "genuineness": 4.545003414154053, "identity": 0.7376540899276733, "hypothesis": "J'ai trouvé la 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_Awe/25efd1273663b69648ed99af67248aa998af2495497cae8d34907bfbb58193e4.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "25fc5f32aba4526e858b76852e6acc0eef0aa3d794857c46ed7f7f2226e4ad1b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "46b3d885bc7069a4c40e864352a1339fbfa769826ba1a6f76ee60e5ac4b3e40c", "generation_seconds_batch": 24.213599503040314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8199821710586548, "target_z": 1.671875073215179, "ce": 6.348263263702393, "genuineness": 4.243753433227539, "identity": 0.4979502856731415, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/25fc5f32aba4526e858b76852e6acc0eef0aa3d794857c46ed7f7f2226e4ad1b.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "260f8a71094207a8e9267a27c8efa51f39f5e186c3a9c0e9a511fd7f252b1545", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "53cfaf7a5e0263adfb265e746edce614282c1597b4d12696e3bc2ebc4a84c96e", "generation_seconds_batch": 28.129786949953996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0952204242348671, "target_z": -0.05468749667203732, "ce": 6.165581703186035, "genuineness": 4.68307638168335, "identity": 0.7281910181045532, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/260f8a71094207a8e9267a27c8efa51f39f5e186c3a9c0e9a511fd7f252b1545.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "2630107a9dc14dc9e6df57e442b4d838ff6f4e3128e41085a691c5662af8fb70", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "3da6b3fedbd6d9d232e1b5246d094cb19deae0213b8580a10efe9eebf8d19741", "generation_seconds_batch": 23.213094190927222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7445544600486755, "target_z": 1.4921875232957387, "ce": 5.95112943649292, "genuineness": 4.595211505889893, "identity": 0.31747615337371826, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/2630107a9dc14dc9e6df57e442b4d838ff6f4e3128e41085a691c5662af8fb70.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "268aa7a34c43b40746bb098de99d7ec71c7b97bb3af8e2cffae850968a793c3d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "27f3001b528480227bf65bc16fafe0f99332a705ee6f4dfcd8fd962c9837204f", "generation_seconds_batch": 22.094267684966326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7054376602172852, "target_z": 3.7812500665592537, "ce": 6.41180419921875, "genuineness": 4.557555198669434, "identity": 0.4372512102127075, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/268aa7a34c43b40746bb098de99d7ec71c7b97bb3af8e2cffae850968a793c3d.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "26de98111db74b1eb29f2214389bb0f3e5b52c4412b660a408bd6a39fe172542", "generation_seconds_batch": 17.006943335058168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11694687604904175, "target_z": -0.0029296898573068996, "ce": 6.546830177307129, "genuineness": 4.268857479095459, "identity": 0.04406818747520447, "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_Awe/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "271557787ef921049b3bd4d9cefa29fe32306daa7e412e830ffccfd7f207ad39", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5ee83a12d24c7830211bc992dbbe3abdc40e67643df8d9d9e41157ed6ed3e069", "generation_seconds_batch": 23.197548842057586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05873637646436691, "target_z": -0.14160156402531623, "ce": 6.09409761428833, "genuineness": 4.325342178344727, "identity": 0.7439893484115601, "hypothesis": "De deur staat nog open. Ik heb je 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_Awe/271557787ef921049b3bd4d9cefa29fe32306daa7e412e830ffccfd7f207ad39.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": "275efc4d866d00a7a9da0d23879bbb2c66b22e5bad8fd832cf943a366bd2b231", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I wrote the number on the envelope.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b1e97f73210941bb298890ed7c6d7ab63ca3df5a445e88b6e63c5c227fd6fb95", "generation_seconds_batch": 15.948158833896741, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4051298499107361, "target_z": 0.6835937616478693, "ce": 6.340320587158203, "genuineness": 4.331617832183838, "identity": 0.4433586895465851, "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_Awe/275efc4d866d00a7a9da0d23879bbb2c66b22e5bad8fd832cf943a366bd2b231.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "2766881e5ac4c2770bc5922f85a25e84a1edf32b84be2cd6b2e919ca8048518c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f831bad972f45af24020e5d5838a6186ac84d8114cb2a949086077f73e586a37", "generation_seconds_batch": 24.19403005694039, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23459768295288086, "target_z": 0.277343766085153, "ce": 6.133810997009277, "genuineness": 4.7081804275512695, "identity": 0.7406902313232422, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/2766881e5ac4c2770bc5922f85a25e84a1edf32b84be2cd6b2e919ca8048518c.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "27d28c6226c9db780ec2f268c09b7aec91f131a9df4a81ae7c36262ff8396eb8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c604514a630a35e2a3236aa902e1857f6a012e257bb4cc7f1412ece875181256", "generation_seconds_batch": 24.339841037988663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32314321398735046, "target_z": 0.4882812228216381, "ce": 6.0146708488464355, "genuineness": 4.545003414154053, "identity": 0.4518851637840271, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/27d28c6226c9db780ec2f268c09b7aec91f131a9df4a81ae7c36262ff8396eb8.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "28cfe68fcc613d80e4874b8752415412117dac86bb72b466a6de01cbc2ecdab8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cb451bfe7fa8b1265d8c874c91687e94200e8df6fa7588f9ab1823a31779ed26", "generation_seconds_batch": 28.104616391006857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1741644144058228, "target_z": 2.5156251841472685, "ce": 5.863759994506836, "genuineness": 4.319066047668457, "identity": 0.7238743305206299, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/28cfe68fcc613d80e4874b8752415412117dac86bb72b466a6de01cbc2ecdab8.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "29070ce7830dcd83f4105fcc2b65aeb1e6fe49f076362d095afdec5967fa3ae8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8f1980c4ef6504d4cf4a36e708138fe79963aa3a9a94d14106ab6666faf6a1ae", "generation_seconds_batch": 22.87917009193916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.296907514333725, "target_z": 0.42578126719447384, "ce": 6.252951145172119, "genuineness": 4.432034492492676, "identity": 0.16860397160053253, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/29070ce7830dcd83f4105fcc2b65aeb1e6fe49f076362d095afdec5967fa3ae8.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "290865d27f3d8c1dee8541c8e2ec082fcb2eb4db24bb2ec19e0165df5251130b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4613d42c1d0ac3f8c194736cee761783201a870e90e1ce9e5c7fb72c91c5600e", "generation_seconds_batch": 26.909323659958318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09030122309923172, "target_z": -0.06640625610126492, "ce": 6.141753673553467, "genuineness": 4.68307638168335, "identity": 0.4762107729911804, "hypothesis": "Die Tür 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_Awe/290865d27f3d8c1dee8541c8e2ec082fcb2eb4db24bb2ec19e0165df5251130b.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "2971421681b7aaa2b8a18101247576f58a6d15b348b58d7837d11304c8ffe2e9", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "20ea616404445354e47c31761cc745b1296e197a0f45fb97888a96d14fd272ba", "generation_seconds_batch": 17.524123965995386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21164143085479736, "target_z": 0.22265626941311564, "ce": 6.229123115539551, "genuineness": 4.6705241203308105, "identity": 0.8819913864135742, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/2971421681b7aaa2b8a18101247576f58a6d15b348b58d7837d11304c8ffe2e9.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "297bd89e36abd920c8e3d8ff85b8ead4a720d0fe39fb6d22cb561aa88d88f9a1", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "dd9b64a06c01c86b89e316166ce7f866a3bd2da4d296d56d3613a9fd966bf4f9", "generation_seconds_batch": 24.120961789041758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8855714797973633, "target_z": 1.828125104276164, "ce": 6.197352409362793, "genuineness": 4.369274139404297, "identity": 0.6344777345657349, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/297bd89e36abd920c8e3d8ff85b8ead4a720d0fe39fb6d22cb561aa88d88f9a1.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": "2a43ae2a6f03b0ea614d372eb8e91cc35b506b730bfc0923bed6967cdb49305d", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8fdf44d4882f0e9141fc8d825e1054be7b2c30abb7b8aac137d600e6dc9ca096", "generation_seconds_batch": 24.357626615907066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.072737693786621, "target_z": 4.65625001331185, "ce": 6.197352409362793, "genuineness": 4.68307638168335, "identity": 0.7471142411231995, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près 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_Awe/2a43ae2a6f03b0ea614d372eb8e91cc35b506b730bfc0923bed6967cdb49305d.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "2a72b0835f3a3413ce5474cc7b806c61b79a31ae8d4f49a354aa8fd2a11fa33b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "77f2e55a4d8401f6203d4d515b21c7e9d5b9dd9bdbad5e202a9a7a6c2a7aa80b", "generation_seconds_batch": 17.55622039292939, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7412750124931335, "target_z": 1.484375064340612, "ce": 6.308549880981445, "genuineness": 4.65797233581543, "identity": 0.6263959407806396, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/2a72b0835f3a3413ce5474cc7b806c61b79a31ae8d4f49a354aa8fd2a11fa33b.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "2aa3a4b1db35e811307b8c65f26cb5222c255e515a073eebc4c54accbf9fa7a6", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "6ea6dbc53ee1d0e8b077e9093ea901f7029e4798bd7c743ea0a433f00c1c3062", "generation_seconds_batch": 16.815395866986364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2903485894203186, "target_z": 0.4101562782876828, "ce": 6.260893821716309, "genuineness": 4.758388519287109, "identity": 0.5094658136367798, "hypothesis": "Die Tür 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_Awe/2aa3a4b1db35e811307b8c65f26cb5222c255e515a073eebc4c54accbf9fa7a6.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "2b43bbd66c0ce9c166446321a9836c360d6c9b528220afb7ed4f3883f9d644a1", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "f621c08446400f946c05289e5ba086310a1ec684cba66a97b12df06a9abba702", "generation_seconds_batch": 24.289364001946524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24115660786628723, "target_z": 0.292968754991944, "ce": 5.9431867599487305, "genuineness": 4.645420074462891, "identity": 0.7350196838378906, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/2b43bbd66c0ce9c166446321a9836c360d6c9b528220afb7ed4f3883f9d644a1.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "2b4644f63cde625af7166c565fc3e278a138621a739b3489618e76e099526bd5", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6b60c077223a1e2faf9b5990c9df90e02c7fa7b92824274e47901f3b4d45f201", "generation_seconds_batch": 22.526593195972964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08210256695747375, "target_z": -0.08593749223475375, "ce": 5.808161735534668, "genuineness": 4.381826400756836, "identity": 0.29573285579681396, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/2b4644f63cde625af7166c565fc3e278a138621a739b3489618e76e099526bd5.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "2c2caee87d4e0f0c16f416fcb5db6caa022238db3649284fd7f7c9fdc6920c04", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6be0c3f33a2c00aa78fe1fe52a1b3420ee230dbaf821d34d2d6126abcd6af776", "generation_seconds_batch": 19.21654908300843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8331000208854675, "target_z": 1.7031250510287612, "ce": 6.221180438995361, "genuineness": 4.457139015197754, "identity": 0.2561871111392975, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/2c2caee87d4e0f0c16f416fcb5db6caa022238db3649284fd7f7c9fdc6920c04.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "2c68cd6e9d2402d804e97f598f3e80a784755ee1a8c07b01c8d0c290d55df842", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "69e3ea525c4daf05f07a8b6a390c57ca67d0bc5f8f1f51341ffa7ad7b7e145e9", "generation_seconds_batch": 25.057579408050515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8790125250816345, "target_z": 1.8125000443728359, "ce": 6.260893821716309, "genuineness": 4.6203155517578125, "identity": 0.8268712162971497, "hypothesis": "J'ai trouvé la 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_Awe/2c68cd6e9d2402d804e97f598f3e80a784755ee1a8c07b01c8d0c290d55df842.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "2cd2c4548ebc7f0a500215cada4e66d836e82a98c1eb0e445588ef1c06950b24", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "6546bb085b0399a1fbf785bca655521e02fbdbb7ad835720b2c4b38529b11903", "generation_seconds_batch": 24.942765551968478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04520858824253082, "target_z": -0.1738281169574235, "ce": 6.284721851348877, "genuineness": 4.6203155517578125, "identity": 0.5245552062988281, "hypothesis": "Die Tür 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_Awe/2cd2c4548ebc7f0a500215cada4e66d836e82a98c1eb0e445588ef1c06950b24.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "2f0fc0aafe164e491f771ce57e63b427c8a371591aec0745e499605d409bb995", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "20b4891275a8bb303f2d79d5d6e0eccf996093aa4347c91d728a7ba8cd4e0945", "generation_seconds_batch": 24.646020950051025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11858660727739334, "target_z": 0.0009765573693908653, "ce": 6.213237762451172, "genuineness": 4.507347106933594, "identity": 0.6458082795143127, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/2f0fc0aafe164e491f771ce57e63b427c8a371591aec0745e499605d409bb995.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "2f45676508f7b028cf28142eeb2592d19446f750c8d174e2a54165b40366f349", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "aa3812f2979c2124f13ef55e92b920e8f05d645d5d0689627b84507bd620feef", "generation_seconds_batch": 23.4675678339554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4627572298049927, "target_z": 3.203124980032224, "ce": 6.41180419921875, "genuineness": 4.758388519287109, "identity": 0.4951215386390686, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/2f45676508f7b028cf28142eeb2592d19446f750c8d174e2a54165b40366f349.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": "3011579b30da2c2c71153c90b596192334a1b5c81149afafae9d5ab5e19c189d", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The keys are on the kitchen table.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "22d49d88f3ea0a52e562dbe20412715af0992d5b91e99b1e94d2fdae4d62da6d", "generation_seconds_batch": 17.756574998027645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3184608221054077, "target_z": 2.859375082089746, "ce": 6.292664527893066, "genuineness": 4.632867813110352, "identity": 0.387264609336853, "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_Awe/3011579b30da2c2c71153c90b596192334a1b5c81149afafae9d5ab5e19c189d.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "304ff8fe28397e978df26bfc3e934df126166fa64b9caddaa407a248886196df", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "20e9dcc8e86791d9bacc946796eb1359d0b5b62caca85fd6b7df95e885be4255", "generation_seconds_batch": 18.505269854911603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39529144763946533, "target_z": 0.6601562427894142, "ce": 6.125868320465088, "genuineness": 4.243753433227539, "identity": 0.4981383979320526, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/304ff8fe28397e978df26bfc3e934df126166fa64b9caddaa407a248886196df.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "3095b2eaad6817cb161e498bd5081a0158ab5a4e133b903b239c1c5dc9561bfc", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "bb162243a05150257d961c4cb575c374673677887f315adf5d465a9d94ec3fc7", "generation_seconds_batch": 28.34590965299867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2255791425704956, "target_z": 0.2558593619654795, "ce": 5.824047088623047, "genuineness": 4.557555198669434, "identity": 0.7389519214630127, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/3095b2eaad6817cb161e498bd5081a0158ab5a4e133b903b239c1c5dc9561bfc.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "315102ee4d195ad0a9db6857774be8e4e2c9505d64457b3066439adb34dc6682", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "658952f37793487b4ac48fca2e50c66aadeb43b9c30099472d0c761de20c598e", "generation_seconds_batch": 24.27643874497153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1676054000854492, "target_z": 2.499999982250866, "ce": 6.046441555023193, "genuineness": 4.607763767242432, "identity": 0.21127769351005554, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/315102ee4d195ad0a9db6857774be8e4e2c9505d64457b3066439adb34dc6682.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "3203199623241ace9db2a6451635a8de4428a7589c4e59875cadb603dba88a64", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "eae9cfc511734a3e5c54529db123ef33ab2282e594e4205cf1080ef7632f0150", "generation_seconds_batch": 20.003797247074544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0841522291302681, "target_z": -0.08105468763866511, "ce": 6.09409761428833, "genuineness": 4.425758361816406, "identity": 0.5958912968635559, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/3203199623241ace9db2a6451635a8de4428a7589c4e59875cadb603dba88a64.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": "329d10004606c712f038e576a9daaa1e671feb6068b1d2c371ceef1d3c610371", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6a5f84c56d8302571883d2b4ac1459996e3ee30bf40d43db7b08dc41ee4fc458", "generation_seconds_batch": 23.014687333954498, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16818851232528687, "target_z": 0.1191406202853862, "ce": 5.8875885009765625, "genuineness": 4.545003414154053, "identity": 0.8052209615707397, "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_Awe/329d10004606c712f038e576a9daaa1e671feb6068b1d2c371ceef1d3c610371.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "32afd472e59716ee153c8c6bc948cb2494aa4fd815a311d6e4a7a66b6f95b26b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5221de448fa351cc942d5a9d88466adb5aaa15e356fca312afb948045f4ad5e1", "generation_seconds_batch": 23.4181006179424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.112091302871704, "target_z": 4.750000088745671, "ce": 6.24500846862793, "genuineness": 4.545003414154053, "identity": 0.33523890376091003, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/32afd472e59716ee153c8c6bc948cb2494aa4fd815a311d6e4a7a66b6f95b26b.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "32cfa4377900a8e95f3193ed1ea387fdb1605bf5c1bd45f37292c422c8c11c3d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "18313a669a15a884ab00eee275c9edb45be40a338a64619e76c76ad88232d4aa", "generation_seconds_batch": 17.492174144019373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23951688408851624, "target_z": 0.28906252551438055, "ce": 6.324435234069824, "genuineness": 4.632867813110352, "identity": 0.34832167625427246, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/32cfa4377900a8e95f3193ed1ea387fdb1605bf5c1bd45f37292c422c8c11c3d.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "32e303b17c4069bc58de31574784ce6a7b418b21c22837aae9093f1dc7615725", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "143c65e9b2518ea26a44a4efe7e948f8e3f56206cb02a88cb99d98baf5042e5e", "generation_seconds_batch": 21.939476790023036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09399062395095825, "target_z": -0.057617186529344215, "ce": 6.125868320465088, "genuineness": 4.15588903427124, "identity": 0.20928089320659637, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/32e303b17c4069bc58de31574784ce6a7b418b21c22837aae9093f1dc7615725.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": "3339c658e51c8ca936ba21a9045c4977f59f24e4b3bcb20ac134dd8d944ef6e9", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "60bf740086dd16c2f42e92a8800a3626e8914bd07424370a6d6bff1365104da0", "generation_seconds_batch": 17.20223418995738, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7150393128395081, "target_z": 1.4218751087134476, "ce": 6.09409761428833, "genuineness": 4.432034492492676, "identity": -0.01634366810321808, "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_Awe/3339c658e51c8ca936ba21a9045c4977f59f24e4b3bcb20ac134dd8d944ef6e9.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": "33496647164875c3da53b8aa668549a1c918a96d719e5ddbaf9799a87ca6f4d6", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Someone moved the little blue chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5e5174f87a95fc86420339405547729574a5f5e7c1131c508022a8f23d97270c", "generation_seconds_batch": 25.272634807042778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1151340007781982, "target_z": 2.375000070996537, "ce": 6.181467056274414, "genuineness": 4.482243061065674, "identity": 0.5212286710739136, "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_Awe/33496647164875c3da53b8aa668549a1c918a96d719e5ddbaf9799a87ca6f4d6.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "337a1917119bf490edcd1ff3c33d3b5538d9190cc2eaed155e050b39943b2acc", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "04489d203e69229b10b1908f7213571ba95604ca19b031902f65cbf6d7bbf7d6", "generation_seconds_batch": 17.806292160064913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9940305948257446, "target_z": 4.468750146430358, "ce": 6.197352409362793, "genuineness": 4.469690799713135, "identity": 0.6472118496894836, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/337a1917119bf490edcd1ff3c33d3b5538d9190cc2eaed155e050b39943b2acc.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "126b541bdc14d2dd749c7193a7c0de63ad319ed622ccdafdc8f37477c70882e4", "generation_seconds_batch": 17.645113862934522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09317075461149216, "target_z": -0.05957031901726025, "ce": 6.054384231567383, "genuineness": 4.293961524963379, "identity": 0.5313209891319275, "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_Awe/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "fcd3b9330672a36115fef08510c0ff99b91a76f81156cd66d01a3366ca3f5aba", "generation_seconds_batch": 17.553265613969415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08661182224750519, "target_z": -0.07519532567318561, "ce": 6.38003396987915, "genuineness": 3.9299514293670654, "identity": 0.24672706425189972, "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_Awe/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "3498592172dd199a83022ac611a063cb767de565958c97404f3cf7f5c66298ee", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0438af3fd8ea76a33517b8c5602b7debc48f4544fc2324bb457de47fd53653a3", "generation_seconds_batch": 17.069245294085704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23787713050842285, "target_z": 0.2851562250402799, "ce": 6.125868320465088, "genuineness": 4.7332844734191895, "identity": 0.7494521141052246, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/3498592172dd199a83022ac611a063cb767de565958c97404f3cf7f5c66298ee.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "3504f030692c2319f813100c84034a1340ad7a6f27872b59abba04ad446a95fd", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8986c00ec08eee33b981ffe5911811b6655a46082c01c9fae8fcabdfe1f1b43b", "generation_seconds_batch": 20.003797247074544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10710848122835159, "target_z": -0.026367190966627794, "ce": 6.117925643920898, "genuineness": 4.7834930419921875, "identity": 0.8153536319732666, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/3504f030692c2319f813100c84034a1340ad7a6f27872b59abba04ad446a95fd.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "3513166ad118e8db67aa6cdb0d823cd1d12c426474158a0bb42dabbe773528dd", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "848dc965bbc6d0ada45561d966d30c5b92947a904b2c519805b0828a3a1f0060", "generation_seconds_batch": 24.202525199041702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0233089923858643, "target_z": 2.156250084308388, "ce": 6.348263263702393, "genuineness": 4.582659721374512, "identity": 0.5147064924240112, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/3513166ad118e8db67aa6cdb0d823cd1d12c426474158a0bb42dabbe773528dd.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "35fef4b82c624d1a4a49af90c4d705e6360d1ee2e9561e6195ba6528fa11f457", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1abf016c281e408ce532fb3c6806bd82da025f21d9cc9b91d031d8cec6b15282", "generation_seconds_batch": 26.76430962199811, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15097132325172424, "target_z": 0.07812499778135822, "ce": 6.300607204437256, "genuineness": 4.7834930419921875, "identity": 0.808103084564209, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/35fef4b82c624d1a4a49af90c4d705e6360d1ee2e9561e6195ba6528fa11f457.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "362b394b6e61d0700b06200a2ca2aa67325505e444b7e3f851d4345dde5202ca", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a31e068e4791a230ead06f259dbc70ed739a7953206eb072972821c0bed28662", "generation_seconds_batch": 18.096543646068312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41824769973754883, "target_z": 0.7148437394614515, "ce": 6.252951145172119, "genuineness": 4.833701133728027, "identity": 0.7337766885757446, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/362b394b6e61d0700b06200a2ca2aa67325505e444b7e3f851d4345dde5202ca.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "364f81b9456cbacd3998c01b3c6282632a4114cdbc726b12620f4d71d23331e7", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "21df3e4f8432d0308c249477e70956cb0d1019d1a8b5523cec90b19bf2a4d9b1", "generation_seconds_batch": 23.261928980937228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5510660409927368, "target_z": 1.0312500310609851, "ce": 6.09409761428833, "genuineness": 4.758388519287109, "identity": 0.7896642088890076, "hypothesis": "J'ai trouvé la 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_Awe/364f81b9456cbacd3998c01b3c6282632a4114cdbc726b12620f4d71d23331e7.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "378357c37aeb860e34fd662b2069417f66770e4b7cabc3c12e1532c6860a7fff", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ab94d8f36dd8150c094ddb8699928e775a8b135bf8ed0cd98e88332aa803ba26", "generation_seconds_batch": 18.024529370944947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16408918797969818, "target_z": 0.10937501109320893, "ce": 6.09409761428833, "genuineness": 4.6705241203308105, "identity": 0.6844372749328613, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/378357c37aeb860e34fd662b2069417f66770e4b7cabc3c12e1532c6860a7fff.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": "3805f899810be072561ee920d9e54af15e9f7ab88a189741d73a9cedd4e182f9", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3762b7a19be974a6923283a2b37b572a1e9f19d97e142abca31c865d8a556567", "generation_seconds_batch": 17.33623949496541, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11079788208007812, "target_z": -0.017578121394707096, "ce": 5.605623245239258, "genuineness": 4.243753433227539, "identity": 0.6798661947250366, "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_Awe/3805f899810be072561ee920d9e54af15e9f7ab88a189741d73a9cedd4e182f9.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": "382c0c78e20f041e2fc6999ed4657054272e5dc6a1c1238d71c1d6f8e3499b08", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "85a76790763c195397d4d7c57e0c59347c9bf681bac9204b51449a707a194672", "generation_seconds_batch": 18.95370879303664, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7841447591781616, "target_z": 3.9687499334407463, "ce": 6.054384231567383, "genuineness": 4.607763767242432, "identity": 0.828204333782196, "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_Awe/382c0c78e20f041e2fc6999ed4657054272e5dc6a1c1238d71c1d6f8e3499b08.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "3842c0e56d871772702ada04e9da87f22d481ce2fe19db7ae870f3e0d121c72f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "bac718f397636360559d79861fba282c2e7f640ed15fdc761d912dd1614f10d8", "generation_seconds_batch": 23.83297951996792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4641602039337158, "target_z": 0.8242187328055262, "ce": 6.284721851348877, "genuineness": 4.356721878051758, "identity": 0.35519200563430786, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/3842c0e56d871772702ada04e9da87f22d481ce2fe19db7ae870f3e0d121c72f.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "385475208f1aa5e1809fe998df39a89190e76fdf5f6cfc1db7acc76be3f1ec50", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4e483a20192363579801ac07ef51b0b5d09cda7a6b1d8064c826a5338701b99c", "generation_seconds_batch": 23.969599514035508, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6297731995582581, "target_z": 1.2187500399355522, "ce": 6.054384231567383, "genuineness": 4.645420074462891, "identity": 0.6588922739028931, "hypothesis": "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_Awe/385475208f1aa5e1809fe998df39a89190e76fdf5f6cfc1db7acc76be3f1ec50.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "38b9ee30ceb992d04630ed38a0d5775a18b61fefb06a65aec5132ac871b6680e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f3723bb654f1401a20af3ce28783bbe857beecf98f7fe1c2206cbf69bfdd4178", "generation_seconds_batch": 23.75589238095563, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0692214965820312, "target_z": 2.2656250776524627, "ce": 5.7406487464904785, "genuineness": 4.143336772918701, "identity": 0.3114371597766876, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/38b9ee30ceb992d04630ed38a0d5775a18b61fefb06a65aec5132ac871b6680e.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "38fc62b818ebf8a235e185f5909d781971bdf5eb32f9a503959d61fd4f1c4d6b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "02d80113ee8d05cce7087ce6a2dabebd7cefeefa04f9b3b053166ed9181cd77e", "generation_seconds_batch": 25.43686308595352, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4412039518356323, "target_z": 0.7695312361334888, "ce": 6.300607204437256, "genuineness": 4.68307638168335, "identity": 0.7654422521591187, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/38fc62b818ebf8a235e185f5909d781971bdf5eb32f9a503959d61fd4f1c4d6b.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "3941c155732c925fa7f75dfd7010cf4d42b1f01ca7dd62d29c5a0847e233593c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8e63614a9d61c5b6f39bcca0307392a6f11bce5bc9965fe17ce54b76765bb3b8", "generation_seconds_batch": 22.459649711032398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5480233430862427, "target_z": 3.4062500488101195, "ce": 6.205295085906982, "genuineness": 4.582659721374512, "identity": 0.5119746327400208, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/3941c155732c925fa7f75dfd7010cf4d42b1f01ca7dd62d29c5a0847e233593c.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "39494a77160dbfd23c425c6ac7764ee2d95ca75a617e853fb4c396113a9a1d3a", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "26665b328d9901193fa4ccd34e1aa843d843e76aa0eaabd64dcc3f09ffd0a201", "generation_seconds_batch": 23.892318962025456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3772543966770172, "target_z": 0.6171875055466045, "ce": 6.23706579208374, "genuineness": 4.406930446624756, "identity": 0.6552641987800598, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/39494a77160dbfd23c425c6ac7764ee2d95ca75a617e853fb4c396113a9a1d3a.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "395f56951b96bcdbeffd7e75c436ac9d0b25249b313fe4b3c26cbebf21dc5174", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3dcd7cb874a91ec5f12ef849359e81b7aa14c7556774c8065c03c41511a3bfc0", "generation_seconds_batch": 23.19738363509532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8888509273529053, "target_z": 1.8359375632312909, "ce": 5.9431867599487305, "genuineness": 4.256305694580078, "identity": 0.5148710012435913, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/395f56951b96bcdbeffd7e75c436ac9d0b25249b313fe4b3c26cbebf21dc5174.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "3978b4c27d8946dce39cbf2d3bc6c296edf185a685c1a9cb1344db56ef2298ce", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0aa4695e808f0b591c84613907554dac0baf74dcd42e612bdf4a6bc5aa29b4c6", "generation_seconds_batch": 22.76199042191729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1599898487329483, "target_z": 0.09960936640276308, "ce": 6.23706579208374, "genuineness": 4.507347106933594, "identity": 0.22165188193321228, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/3978b4c27d8946dce39cbf2d3bc6c296edf185a685c1a9cb1344db56ef2298ce.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": "39c67f4ca4696faebaa628488457fd4439ba85e087903fbe2f93cec23782ff66", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "205839ed0d1ba2358ea443dd3e0720795bcbeac738e364c482c80263db5de09d", "generation_seconds_batch": 17.19543138402514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10546875, "target_z": -0.03027343819332556, "ce": 6.09409761428833, "genuineness": 4.293961524963379, "identity": 0.39046424627304077, "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_Awe/39c67f4ca4696faebaa628488457fd4439ba85e087903fbe2f93cec23782ff66.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "39cb3beaebdd999651c6e9c1821c0140afa4d5a950b41d5be7a2d9c4e6c89fc8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "89666512b438ab2b48c4a88360e843168cb1e575c464f77800f64a00f4a2ba3f", "generation_seconds_batch": 23.963510739966296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2725483179092407, "target_z": 2.7500000887456717, "ce": 6.427689552307129, "genuineness": 4.65797233581543, "identity": 0.7004657983779907, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/39cb3beaebdd999651c6e9c1821c0140afa4d5a950b41d5be7a2d9c4e6c89fc8.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "39f54ed568c971e2cdbb4e48625019d5a8dcec8d0ffc2cd6b595dbbdedc8ec5c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "689fd731d597eeb347a1a7dc77ce5f847b50923e0f1f99826dc1ef9a766a864f", "generation_seconds_batch": 23.112113401060924, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8265410661697388, "target_z": 1.687499991125433, "ce": 6.24500846862793, "genuineness": 4.331617832183838, "identity": 0.5507943630218506, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/39f54ed568c971e2cdbb4e48625019d5a8dcec8d0ffc2cd6b595dbbdedc8ec5c.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": "3ac42b4525d7382e63906d5c20177cfc4172a841537728e2b016ceb33b316334", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "24f34e2f2eef7dbe4bed776135eef09fac66657e5848dd62507859d75d3aafe8", "generation_seconds_batch": 17.379140036995523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.374448537826538, "target_z": 5.375000212989612, "ce": 5.9431867599487305, "genuineness": 4.369274139404297, "identity": 0.417482852935791, "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_Awe/3ac42b4525d7382e63906d5c20177cfc4172a841537728e2b016ceb33b316334.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "3b2e85c41fbf6a9c36da08a87e0084eef176a47f3a1f78de70d5afac6bb54bc0", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "63dfb0a102db20f832b505d9f7db92e25851f6bf34c27712f65265b1997f5d83", "generation_seconds_batch": 23.80236785695888, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0298678874969482, "target_z": 2.1718750022186417, "ce": 5.847874641418457, "genuineness": 4.394378662109375, "identity": 0.442695677280426, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/3b2e85c41fbf6a9c36da08a87e0084eef176a47f3a1f78de70d5afac6bb54bc0.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": "3b3cc87067b0aed3bdebdcf01e4f52eccc00ad45318edaef3e0ef4eaad55827b", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "680da88b963152c49e4145ec808b644a9e35066de654f872eab667a842426dee", "generation_seconds_batch": 18.74349991697818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6232143044471741, "target_z": 1.2031251220252983, "ce": 5.974957466125488, "genuineness": 4.030367851257324, "identity": 0.4320675730705261, "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_Awe/3b3cc87067b0aed3bdebdcf01e4f52eccc00ad45318edaef3e0ef4eaad55827b.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": "3b47374c4021b53908bd00dbf66113661fc1cb43e8e5f41e0d3e0b69f6c0b0dd", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The road turns left behind the bridge.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "001e986b0b0f35e6ff85ca1fd5103de7c358574739fb1c1afae05b9ff6e2a16a", "generation_seconds_batch": 22.908827190985903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3906090259552002, "target_z": 3.031250031060985, "ce": 6.24500846862793, "genuineness": 4.394378662109375, "identity": 0.41970422863960266, "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_Awe/3b47374c4021b53908bd00dbf66113661fc1cb43e8e5f41e0d3e0b69f6c0b0dd.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "3b6743651b0ffd9cf0a83ac37e6ea02714aedafd92683cca990c14f3792c7ff8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "f760f517b59ed12cca8f2a1c5f6de34a8f3df258ab1acfbaf948c8312700bd14", "generation_seconds_batch": 16.889168279012665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16900837421417236, "target_z": 0.12109373502416793, "ce": 5.974957466125488, "genuineness": 4.7332844734191895, "identity": 0.6860718727111816, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/3b6743651b0ffd9cf0a83ac37e6ea02714aedafd92683cca990c14f3792c7ff8.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": "3bb6c4080cd79e5a5d3d1b9569f54a623de3777866e302404ebef4ad2e97134c", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "252c9b0117d58990c752a6d2ccb68a228f941ea420e95e8e81655cdfdca3ead8", "generation_seconds_batch": 17.80240192601923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5283465385437012, "target_z": 3.359375011093209, "ce": 6.006728172302246, "genuineness": 4.356721878051758, "identity": 0.46484076976776123, "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_Awe/3bb6c4080cd79e5a5d3d1b9569f54a623de3777866e302404ebef4ad2e97134c.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "92df85e73060a062e81445f92640f136a93c460706f5da075579a92200daf23b", "generation_seconds_batch": 17.929084462928586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2247592806816101, "target_z": 0.25390624722669775, "ce": 6.125868320465088, "genuineness": 4.337893962860107, "identity": 0.5960385203361511, "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_Awe/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.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": "3c8438f67de7efa2f059e3a86709b2fb362a7883fb56475b9ebe95e179af4b2c", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Your message arrived after I had left.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6760e17127a9646e2e2592c885191df46685b16c5dd5991f7f4f50f9b1403eb6", "generation_seconds_batch": 23.786815706058405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4100490212440491, "target_z": 0.6953124500805598, "ce": 6.252951145172119, "genuineness": 4.425758361816406, "identity": 0.4828375577926636, "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_Awe/3c8438f67de7efa2f059e3a86709b2fb362a7883fb56475b9ebe95e179af4b2c.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": "3cecd1c4ee43350923d82599523cf60ba150d4b15d62c6c42938d00b39500211", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dcfe61da6dbd49ce146c0d83b2315145598327b1bee14285e42ca6f2ead38017", "generation_seconds_batch": 17.79366643796675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2528715133666992, "target_z": 2.703125051028761, "ce": 6.0305562019348145, "genuineness": 4.632867813110352, "identity": 0.5175950527191162, "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_Awe/3cecd1c4ee43350923d82599523cf60ba150d4b15d62c6c42938d00b39500211.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "3d61fa86523d045cbe749889a2a6edf87a9c61292ea558a28e1407c75e0286ff", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "91a81913b645234d6a5900d0782635b70849199a14bb33d7728df25cb9685993", "generation_seconds_batch": 19.34842471103184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5313892364501953, "target_z": 0.9843749933440746, "ce": 6.125868320465088, "genuineness": 4.457139015197754, "identity": 0.5890264511108398, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/3d61fa86523d045cbe749889a2a6edf87a9c61292ea558a28e1407c75e0286ff.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "3d7ebdc56f0d565b65c872566d899db77fe52a85b55a7923f1961ff6d618e31a", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c6bec07ed9a36d94762200e19a798cd0982cd2d42a719da250da66c6d0e09952", "generation_seconds_batch": 23.89384314895142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1348108053207397, "target_z": 2.4218751087134476, "ce": 6.38003396987915, "genuineness": 4.8588056564331055, "identity": 0.8531234264373779, "hypothesis": "J'ai trouvé la 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_Awe/3d7ebdc56f0d565b65c872566d899db77fe52a85b55a7923f1961ff6d618e31a.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": "3e06f708cce943f97de36be9fa9b5418941f79d467c7bee5da736ebf4c2f17d7", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0356e5f5ee4c7da198f929ad00c08b7f82fc4db3e191dd136c4c0ff7e8c1322a", "generation_seconds_batch": 23.42671022308059, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45596155524253845, "target_z": 0.8046875144211716, "ce": 6.268836498260498, "genuineness": 4.419482707977295, "identity": 0.4514692425727844, "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_Awe/3e06f708cce943f97de36be9fa9b5418941f79d467c7bee5da736ebf4c2f17d7.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "3e5e85c564356ac6ec6e8fa353e1e373160681b40f2a1fba1d79c758d38a9cd4", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78f5335191fc7658ecfdf3a2508e3f56fc361a14b9782fae0a5d85260320375a", "generation_seconds_batch": 24.190890930010937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0298678874969482, "target_z": 2.1718750022186417, "ce": 6.181467056274414, "genuineness": 4.394378662109375, "identity": 0.44693687558174133, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/3e5e85c564356ac6ec6e8fa353e1e373160681b40f2a1fba1d79c758d38a9cd4.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "3f0a253ff1f74bceafdb8b9e88e442c889d71e7f5c24f6c06df7599a9aa37f5d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f94c7501c165fd0dec924a731a42be6309b0fb86e1d4439b26e5236851d3aa06", "generation_seconds_batch": 17.527516140020452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18663549423217773, "target_z": 0.16308591489758678, "ce": 6.23706579208374, "genuineness": 4.344170093536377, "identity": 0.4919499158859253, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/3f0a253ff1f74bceafdb8b9e88e442c889d71e7f5c24f6c06df7599a9aa37f5d.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "3f635112fac56f06c126e376912b319386f741a0cccd6c99487b426252044144", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "518ba76ad97b728cc6cd12b9fb1d74d58c9d59c97e3a11ac82a6289cb865ecc6", "generation_seconds_batch": 17.993706298060715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25837379693984985, "target_z": 0.333984377495972, "ce": 6.300607204437256, "genuineness": 4.507347106933594, "identity": 0.5707125663757324, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/3f635112fac56f06c126e376912b319386f741a0cccd6c99487b426252044144.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "3f8d2794096bbc446d47721f32dc4dd89d925f1a1d0537861bc52a51c5ea95d4", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4dfdc0b4208fac34ec7227c8e5db59873d2b1fcbb4903b9f64164d3e96a62325", "generation_seconds_batch": 23.877082450082526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11899654567241669, "target_z": 0.001953132487916034, "ce": 6.022613525390625, "genuineness": 4.337893962860107, "identity": 0.12688280642032623, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/3f8d2794096bbc446d47721f32dc4dd89d925f1a1d0537861bc52a51c5ea95d4.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "4018426f6b33f1b42c52d8f258d3343a13fa77c3d41ed24aa222a10483214ee8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "975d813abb045a2846ba4f3f33a19be3618ce80da2c8df5306ff57c3985985e3", "generation_seconds_batch": 23.969599514035508, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0888983011245728, "target_z": 2.312500115369373, "ce": 6.181467056274414, "genuineness": 4.6203155517578125, "identity": 0.6373658776283264, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/4018426f6b33f1b42c52d8f258d3343a13fa77c3d41ed24aa222a10483214ee8.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "401b8e24d393dce493b222fd49dcac23fb887c2b752f4661875925c3c0510af1", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "8c9bd46ac0b649c190d8545c325cad7c42edad62ef01654d360e710afaee2e4f", "generation_seconds_batch": 21.066820133011788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17679710686206818, "target_z": 0.1396484315374002, "ce": 6.260893821716309, "genuineness": 4.607763767242432, "identity": 0.6694197058677673, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/401b8e24d393dce493b222fd49dcac23fb887c2b752f4661875925c3c0510af1.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "4057cba2adffe5dd054780fd2cef175355637221626f2cd28f406b6997356b05", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "9fe965234d5b95dc8ebaca384e08526fbfe555fd11fbe97a716362cfc82f921e", "generation_seconds_batch": 24.474330081953667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8298205733299255, "target_z": 1.6953125920736343, "ce": 6.435632705688477, "genuineness": 4.432034492492676, "identity": 0.4997837543487549, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/4057cba2adffe5dd054780fd2cef175355637221626f2cd28f406b6997356b05.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "406e7bbd9f6d4a48002fb86cbb4f7dacd63c72c228622bcd0902c1a33ce44804", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bae639dd56e5896da7fa87e8b0ced4615b72408f079e89ef5d032b0902e29dde", "generation_seconds_batch": 28.104616391006857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2397536039352417, "target_z": 2.6718749312221046, "ce": 5.704906940460205, "genuineness": 4.482243061065674, "identity": 0.7247285842895508, "hypothesis": "J'ai trouvé la 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_Awe/406e7bbd9f6d4a48002fb86cbb4f7dacd63c72c228622bcd0902c1a33ce44804.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "40e0560b2f2d12df86d0b693f2e9b87334ba03c7b0e3354988e3083c110c3a8d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "07dbb2c45b2cdc462d0834e8bbccd53db635fd1aa9be420fe26f4720ba802b4f", "generation_seconds_batch": 16.870462088962086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5297495126724243, "target_z": 0.9804687638665112, "ce": 6.38797664642334, "genuineness": 4.469690799713135, "identity": 0.645294189453125, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/40e0560b2f2d12df86d0b693f2e9b87334ba03c7b0e3354988e3083c110c3a8d.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "40f4758771771f6c3723c6727ebe92561f09b7bb08f8e0b4d3c449fc0e62d9dc", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1ca0d7fecb687612147a09423ab8be391ac79d14f29239b4917fbde264dd83c4", "generation_seconds_batch": 18.194606133038178, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05750657618045807, "target_z": -0.14453125388262314, "ce": 6.1894097328186035, "genuineness": 4.545003414154053, "identity": 0.689975917339325, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/40f4758771771f6c3723c6727ebe92561f09b7bb08f8e0b4d3c449fc0e62d9dc.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "416c0686b0d48fbeb7e522d8b321a96c3eecd1fd62edd5a090b7677b52cf8cc6", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "83dd416c7ee754a758a73ccd5d1310f6f0b2788ba13708fe8890a06ebeacfee4", "generation_seconds_batch": 22.677206362015568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4496394395828247, "target_z": 3.1718751442117163, "ce": 6.3641486167907715, "genuineness": 4.68307638168335, "identity": 0.5995569229125977, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/416c0686b0d48fbeb7e522d8b321a96c3eecd1fd62edd5a090b7677b52cf8cc6.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": "41957ded475056d5d84a532ba6722e62a5f9d144320f403cbbc1acf2bd5a6ae9", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Someone moved the little blue chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "82046e91d75c3a7dee252a22134f6b1effb87abb8fcd913ca187562e7d73f409", "generation_seconds_batch": 17.519703989033587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1216928958892822, "target_z": 2.390624988906791, "ce": 6.3641486167907715, "genuineness": 4.482243061065674, "identity": 0.1629268378019333, "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_Awe/41957ded475056d5d84a532ba6722e62a5f9d144320f403cbbc1acf2bd5a6ae9.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "41acbbd51db78ad0b76ed25f6bc7fba615581d3303e0df97103a9d22e4e6c92b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "cfb2c2fa26ab8c2617e37deb64becc996acc67a4f0c3a06e6de55c94cf88d13c", "generation_seconds_batch": 27.513061195029877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2723115086555481, "target_z": 0.36718747004833585, "ce": 5.657250881195068, "genuineness": 4.6705241203308105, "identity": 0.6865769624710083, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/41acbbd51db78ad0b76ed25f6bc7fba615581d3303e0df97103a9d22e4e6c92b.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "41c57d2157d5224b7d45ec052ec13325543de9738bdc921f6aba7585ecbd43d5", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "888c1cdbf6d4229998f2208e649d6d45ba1188c89dd5e3bd13422e1b8538aa0f", "generation_seconds_batch": 16.825003935955465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7937464714050293, "target_z": 1.6093751175880147, "ce": 6.260893821716309, "genuineness": 4.293961524963379, "identity": 0.43555980920791626, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/41c57d2157d5224b7d45ec052ec13325543de9738bdc921f6aba7585ecbd43d5.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": "42769397151e515a4e39bff852a62d9ced235b7bc6c9b0fab0fdfc1c5c6a8c64", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The road turns left behind the bridge.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "89a1136c677fcce37ba22b828337fa503b92557aea1e9aa0182e780dd23eb1f1", "generation_seconds_batch": 16.697118956013583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45924100279808044, "target_z": 0.8124999733762985, "ce": 6.340320587158203, "genuineness": 4.337893962860107, "identity": 0.45706379413604736, "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_Awe/42769397151e515a4e39bff852a62d9ced235b7bc6c9b0fab0fdfc1c5c6a8c64.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "43075db7dae6386052b881d87dfd2c7217b366c32817948b228b71e09f4f209c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7b51deeeab1a9a3b9937c1483266ce2ce79f4bee5b5863b123f2f6bd903af3f3", "generation_seconds_batch": 24.186105314991437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7052009105682373, "target_z": 1.3984375898549923, "ce": 6.022613525390625, "genuineness": 4.331617832183838, "identity": 0.37149909138679504, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/43075db7dae6386052b881d87dfd2c7217b366c32817948b228b71e09f4f209c.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "43466b92dbdfc7ea1714824b7661725d633453910236cfeb1509b40931a501ca", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "da608084176337854a8eea55ba76a94c18dfc0977be506b04879ee086b50e11c", "generation_seconds_batch": 27.429494134965353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21902021765708923, "target_z": 0.24023437305868844, "ce": 6.300607204437256, "genuineness": 4.419482707977295, "identity": 0.6400575637817383, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/43466b92dbdfc7ea1714824b7661725d633453910236cfeb1509b40931a501ca.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "9b76c99fd90049712e63f500b79069d1da698d55e5b2a65583dd3cc8e658311a", "generation_seconds_batch": 17.645113862934522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09645022451877594, "target_z": -0.05175780681473042, "ce": 6.133810997009277, "genuineness": 4.3504462242126465, "identity": 0.734291672706604, "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_Awe/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.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": "437b630fb884afef421fa6cb2579faacc0b03d9a0be28164712694cab486e435", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "764fa5483664e5a7643ad85e9b852e5bccc45a865443eea12f410119adfb49f1", "generation_seconds_batch": 17.200135480961762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5412276387214661, "target_z": 1.0078125122025299, "ce": 6.229123115539551, "genuineness": 4.369274139404297, "identity": 0.5503810048103333, "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_Awe/437b630fb884afef421fa6cb2579faacc0b03d9a0be28164712694cab486e435.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "43c16d12fb479ba08a220c5b732f409b073fc5828d82f03dcb01b22a1f3e5b23", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ada894ea84979a47975fdcf52cb4003050468c28c3d706a2ed96c6b569efc9cd", "generation_seconds_batch": 21.274989960016683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43628475069999695, "target_z": 0.7578124767042612, "ce": 6.221180438995361, "genuineness": 4.300237655639648, "identity": 0.5737621784210205, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/43c16d12fb479ba08a220c5b732f409b073fc5828d82f03dcb01b22a1f3e5b23.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "43ccf4c7e749b031c4c827adfda18285b998f58ac621c13ddfed999e947ef22e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c743a531320b75fe64d6876cd4ab94be19411401762e5ea28cea3010728a3a66", "generation_seconds_batch": 18.126222689985298, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16142462193965912, "target_z": 0.1030273526938997, "ce": 6.221180438995361, "genuineness": 4.306513786315918, "identity": 0.15479028224945068, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/43ccf4c7e749b031c4c827adfda18285b998f58ac621c13ddfed999e947ef22e.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "35d7fb90a5110a6cea2eb06e095897c029132cd214628aea2abd1ecf51468356", "generation_seconds_batch": 20.360484486911446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7281571626663208, "target_z": 1.4531250865270298, "ce": 6.229123115539551, "genuineness": 4.6203155517578125, "identity": 0.6299745440483093, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "4409755e116cfb6b277d0dfce4d971d54b25ca459b5bf8aebf2a9d02cebdeac8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bf639f0a6c8dc85ec3851e8ef119e13dec26869d713c4a14546b45ceebf89adc", "generation_seconds_batch": 16.70946774201002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1413697004318237, "target_z": 2.4375000266237015, "ce": 6.252951145172119, "genuineness": 4.68307638168335, "identity": 0.35270482301712036, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/4409755e116cfb6b277d0dfce4d971d54b25ca459b5bf8aebf2a9d02cebdeac8.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": "4421d9fd8907fbf46cf4bdb5fe7ce878de1c59e266569fcd5729a3210693b98b", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cd866146b9dff98256dd75ae53e3936f6bada86416da21e5bb01d4297269e4d0", "generation_seconds_batch": 23.2968109321082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32806241512298584, "target_z": 0.49999998225086567, "ce": 5.577824115753174, "genuineness": 3.9676074981689453, "identity": 0.4723973572254181, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/4421d9fd8907fbf46cf4bdb5fe7ce878de1c59e266569fcd5729a3210693b98b.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": "4436c26742d7636563140aa99a189aa85b2d2a7cf1e21cf228e6c62a05fc9ea4", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "1ded4b59fb2d2931cc9892340e6b0eb37ba829acdc16568066bf5b0a39fea935", "generation_seconds_batch": 17.33623949496541, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10341908782720566, "target_z": -0.03515624278941419, "ce": 5.661221981048584, "genuineness": 4.532451152801514, "identity": 0.7432194948196411, "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": 0.120000000000001, "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_Awe/4436c26742d7636563140aa99a189aa85b2d2a7cf1e21cf228e6c62a05fc9ea4.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "44a8b9dae1e1af142e36941eb4cf6d934c0b60471e2db599c43e97b0ecdb552d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d94d0fe1a4054c21429145a188e48ad5d36a4d5f667c2c8aa7dafed874ec4f7a", "generation_seconds_batch": 24.715256360010244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3116650879383087, "target_z": 0.46093747448561945, "ce": 6.38797664642334, "genuineness": 4.494794845581055, "identity": 0.29730498790740967, "hypothesis": "The 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_Awe/44a8b9dae1e1af142e36941eb4cf6d934c0b60471e2db599c43e97b0ecdb552d.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "45000e3928e6e960e2717cc27a7111c361df2cff8eb3f6339d87e8d938abdfbf", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "c92457d61d83fccc51da745e59849b01e848f4ae414cfc6795b7a49039e93ee6", "generation_seconds_batch": 16.85214759595692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15814515948295593, "target_z": 0.09521485824050417, "ce": 6.229123115539551, "genuineness": 4.582659721374512, "identity": 0.6601585149765015, "hypothesis": "Die Tür 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_Awe/45000e3928e6e960e2717cc27a7111c361df2cff8eb3f6339d87e8d938abdfbf.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "45026f3d6f3e8a27444ac781dcc16323e12113e2e8e024a368daafd8757c281c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0bb7d28bcece2b34963f731f3778c5e8ff8900c5512e72769fa2781f9c32b82f", "generation_seconds_batch": 25.283767410903238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07800322771072388, "target_z": -0.0957031369251996, "ce": 6.062326908111572, "genuineness": 4.281409740447998, "identity": 0.6215585470199585, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/45026f3d6f3e8a27444ac781dcc16323e12113e2e8e024a368daafd8757c281c.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "45099c1de00ed0243b02114cf5ba728b9bbed2c5fefec949b3104c9aa845a2ce", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1a6a3fa559409aae424c9dd819de5ae40c2857de1e495d9785dcf24234a108cb", "generation_seconds_batch": 26.927808119915426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3906090259552002, "target_z": 3.031250031060985, "ce": 5.577824115753174, "genuineness": 4.319066047668457, "identity": 0.2236488312482834, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/45099c1de00ed0243b02114cf5ba728b9bbed2c5fefec949b3104c9aa845a2ce.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": "4537fed7245a11bf6cd73446b3c8fbef798833fe86a7f70ac6e1c6a957d9afc3", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7fcfd36264565900621da55a1e397609ce46f00edba875aedf7b3d2f5444b718", "generation_seconds_batch": 17.34593644097913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14933159947395325, "target_z": 0.07421876830379476, "ce": 6.284721851348877, "genuineness": 4.425758361816406, "identity": 0.4033084511756897, "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_Awe/4537fed7245a11bf6cd73446b3c8fbef798833fe86a7f70ac6e1c6a957d9afc3.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "453e18cecd5058df9137263710eb1f93779c1f4487808df19bd5c9732f1143d3", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "7fdf049213b4d002a54b251dab96733734ee474200aa81487036757119b209cb", "generation_seconds_batch": 18.20630815590266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5677001476287842, "target_z": 3.4531250865270295, "ce": 6.538887023925781, "genuineness": 4.720732688903809, "identity": 0.5357562899589539, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/453e18cecd5058df9137263710eb1f93779c1f4487808df19bd5c9732f1143d3.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "4543bf831df57ee6cb45872bf991d21315ae29cfc9f1fb6a9f2a69a7e014bdb7", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a49303c665053e2e65dac7f76c229482d2551be1f780da4ae356a3735f515928", "generation_seconds_batch": 26.395248327986337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2987840175628662, "target_z": 2.8125000443728356, "ce": 6.109982967376709, "genuineness": 4.545003414154053, "identity": 0.5576786994934082, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/4543bf831df57ee6cb45872bf991d21315ae29cfc9f1fb6a9f2a69a7e014bdb7.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "45e5c704e399cd5335575bb5a904642d8162c962e2054a0fabfdd4eb60e2e9aa", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1e8622a92e1b857276ee4702fa4adb248a83edae67f44e91b98eae0747716672", "generation_seconds_batch": 24.423128824913874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9284412860870361, "target_z": 4.312500115369373, "ce": 5.855817794799805, "genuineness": 4.231201171875, "identity": 0.2603626251220703, "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_Awe/45e5c704e399cd5335575bb5a904642d8162c962e2054a0fabfdd4eb60e2e9aa.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "45f23401efcd95981e96f7c3b0432d3a62817d43b58f7d0e161b73df5e528d04", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "47a265134bf185dc486fc857a18521ba48302f5356b5a2c969e41daee11f01cd", "generation_seconds_batch": 26.578823543037288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1544876098632812, "target_z": 2.468750146430358, "ce": 6.038498878479004, "genuineness": 4.65797233581543, "identity": 0.4494136571884155, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/45f23401efcd95981e96f7c3b0432d3a62817d43b58f7d0e161b73df5e528d04.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "9cd60a3420ce4b35915380dee2b8f9856c033f3264ec816fc272f48d51627a95", "generation_seconds_batch": 18.441255001933314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11243761330842972, "target_z": -0.01367187416800933, "ce": 6.356205940246582, "genuineness": 4.15588903427124, "identity": 0.554502010345459, "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_Awe/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "460373617f21b4b2e95951352ead74bfd265aa411d62127f220a3b37ee8fabc9", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "712a236d5dae80c2abd60c1ef74dc27894260b8bfcf86351e894afdb0b058142", "generation_seconds_batch": 23.64946450095158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4494026005268097, "target_z": 0.7890624545178433, "ce": 6.459460258483887, "genuineness": 4.344170093536377, "identity": 0.6211881041526794, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/460373617f21b4b2e95951352ead74bfd265aa411d62127f220a3b37ee8fabc9.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "4658a6f814aad9945da22c3fe9ad6f67d0ad518910c6f4e402b0a7893fba0ba0", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "60fec452569e4c776a8095c262e0d74cf5c30ebee3d7fbc4e26a5cd7c4787edf", "generation_seconds_batch": 25.187756229075603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4248066246509552, "target_z": 0.7304687283682426, "ce": 5.796247482299805, "genuineness": 4.482243061065674, "identity": 0.7057299613952637, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/4658a6f814aad9945da22c3fe9ad6f67d0ad518910c6f4e402b0a7893fba0ba0.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "468d0843f400e7a2667552da5625fe00b7cd78170df7dbf685b55575467b432d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7fd4c8ac908faa43fcc0c7f2d63e982d061a0df438774a174fa45ce808ab87f1", "generation_seconds_batch": 24.365749898017384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.252634733915329, "target_z": 0.3203125033279627, "ce": 6.086154937744141, "genuineness": 4.808597087860107, "identity": 0.7430769205093384, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/468d0843f400e7a2667552da5625fe00b7cd78170df7dbf685b55575467b432d.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "479de4034e729d428e4cb286369c8a75df3bf2dd6c57c762cf9053f7c8f8d9a2", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8b585823c440797ff35fcb23464fb77132fdf14c7b3ac20823fff1f181b3d943", "generation_seconds_batch": 22.735881231026724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8199821710586548, "target_z": 1.671875073215179, "ce": 6.141753673553467, "genuineness": 4.68307638168335, "identity": 0.7173919677734375, "hypothesis": "J'ai trouvé la 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_Awe/479de4034e729d428e4cb286369c8a75df3bf2dd6c57c762cf9053f7c8f8d9a2.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "5bf0d7dd2f27bb61696764b9ecf24d3d94844b50affa5f6012412e2b1eb50596", "generation_seconds_batch": 16.511451895930804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9282044768333435, "target_z": 1.9296874966720374, "ce": 6.173524379730225, "genuineness": 4.507347106933594, "identity": 0.5950348973274231, "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_Awe/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "47f528f55abe4e85cb1fca22ce913123d215825ff1e6531c38560474660e77e0", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3e9c88af65cc22f98f4c0b299cb7aa5c101f7cdbf4314479d1b6fbd89d8e6a8d", "generation_seconds_batch": 16.85214759595692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04356884956359863, "target_z": -0.17773438193325558, "ce": 6.173524379730225, "genuineness": 4.432034492492676, "identity": 0.48961883783340454, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/47f528f55abe4e85cb1fca22ce913123d215825ff1e6531c38560474660e77e0.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "4818e1d1029a8f739d335aabeaa0da0689db9777e41398a02c72d632879de158", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ed883638c19fda6b87a98f7f903ca1677ac6e74412d86dd4e9eb9a13342d0f5c", "generation_seconds_batch": 17.761393680004403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4690794050693512, "target_z": 0.8359374922347538, "ce": 6.284721851348877, "genuineness": 4.20609712600708, "identity": 0.4013580083847046, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/4818e1d1029a8f739d335aabeaa0da0689db9777e41398a02c72d632879de158.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "48dee3b9c7c66dc723e005054e280ee68401c9c0d02ce9715b4f84e11f642e47", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "460b407a3c88fb58d62dab7df4fae55cd5ce97a1dd94dc7ea5a41475dbad3e1b", "generation_seconds_batch": 17.217161747976206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4561983346939087, "target_z": 3.1875000621219702, "ce": 6.395919322967529, "genuineness": 4.545003414154053, "identity": 0.5406086444854736, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/48dee3b9c7c66dc723e005054e280ee68401c9c0d02ce9715b4f84e11f642e47.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": "49550bb42c0c4657d813f1cd5da33a5c346e3a9cdf9ad8cc0971e1e02996eb2c", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "39928c7c244c2c8e0ae313187c6a055f087b00bc35eec8a9a4534516cb3b9837", "generation_seconds_batch": 18.318146887002513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.296907514333725, "target_z": 0.42578126719447384, "ce": 6.1894097328186035, "genuineness": 4.331617832183838, "identity": 0.6160144209861755, "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_Awe/49550bb42c0c4657d813f1cd5da33a5c346e3a9cdf9ad8cc0971e1e02996eb2c.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": "49ac3edd072edf8e782c3338cc54a9c2129e4f28ab44eeb27da6cd867b07fe9d", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "19a8ad09003bbf7a3f7fcef3f997ebc4b0b2d419ddf2253fcd7c1bca68497188", "generation_seconds_batch": 17.1468774729874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24033674597740173, "target_z": 0.2910156402531623, "ce": 6.324435234069824, "genuineness": 4.65797233581543, "identity": 0.5538201332092285, "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_Awe/49ac3edd072edf8e782c3338cc54a9c2129e4f28ab44eeb27da6cd867b07fe9d.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fb8c6355e64a943d1828d5164dff05eeae499590f151d3356abcc11de952a604", "generation_seconds_batch": 17.878399697947316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5674633383750916, "target_z": 1.070312467829694, "ce": 6.252951145172119, "genuineness": 4.337893962860107, "identity": 0.5668728351593018, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.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": "4a20204353193b1661baf252acaac5191f3bf0591b288e33655ec7e3a3318da3", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fcde1beea1e68b5a5dc5f40df980f5b3aecb1b7ccd104a8c161239069b5b22c6", "generation_seconds_batch": 17.27704958897084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2641128599643707, "target_z": 0.34765625166398134, "ce": 6.046441555023193, "genuineness": 4.758388519287109, "identity": 0.5765153169631958, "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_Awe/4a20204353193b1661baf252acaac5191f3bf0591b288e33655ec7e3a3318da3.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "4a429edf0031b506e9343dd2980607d44a7382c107142128114a9b6dfef25bb8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f34492c6d5bc04bc5b19104f98c4cc9eb5a3d87cd35c1fcdc151a26961bfdd47", "generation_seconds_batch": 31.063843147014268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06365557014942169, "target_z": -0.12988282234522294, "ce": 6.356205940246582, "genuineness": 4.595211505889893, "identity": 0.32320261001586914, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/4a429edf0031b506e9343dd2980607d44a7382c107142128114a9b6dfef25bb8.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "4b62b1c04abe62308088a42834246c367c90386fefce9a95e740d689efae47ba", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f381500e95e54ed12a8fa015635971d48e033c09b8bff4a64e40b3f5c50c6060", "generation_seconds_batch": 24.058495840989053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11120781302452087, "target_z": -0.01660156402531623, "ce": 6.308549880981445, "genuineness": 4.758388519287109, "identity": 0.7011354565620422, "hypothesis": "Die Tür 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_Awe/4b62b1c04abe62308088a42834246c367c90386fefce9a95e740d689efae47ba.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "4bc006e0dce6b4905e7166716a923c28e42a502a3d67ca32b4501e8e079b5cbb", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "73080b117b8be110ce564746c6d31e5eca71a3ed3409a5bcb519906c5d6fd1aa", "generation_seconds_batch": 23.507644859026186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4198874235153198, "target_z": 0.718749968939015, "ce": 6.292664527893066, "genuineness": 4.406930446624756, "identity": 0.5973921418190002, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/4bc006e0dce6b4905e7166716a923c28e42a502a3d67ca32b4501e8e079b5cbb.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "4c0ca0826e4528838ad1d1237230b8988918f551f4e6a35b4b22c0ae042715c6", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a77d910160175b73cc7c0b5757beb872a9ac452504224cd1b52661dfb94dc888", "generation_seconds_batch": 16.45134605304338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7513501644134521, "target_z": 3.890625059903328, "ce": 6.316492557525635, "genuineness": 4.507347106933594, "identity": 0.5528801679611206, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/4c0ca0826e4528838ad1d1237230b8988918f551f4e6a35b4b22c0ae042715c6.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "4c4525a3f4a8329e689967e1b8f3e95a1b2a8212c1a9344c344b87e86530053b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "938c9ba50bffe35c91be8ea761a97656f9c0b219517a73c900a3f664a949d721", "generation_seconds_batch": 23.50782528903801, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0888983011245728, "target_z": 2.312500115369373, "ce": 5.792276382446289, "genuineness": 4.325342178344727, "identity": 0.43130409717559814, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/4c4525a3f4a8329e689967e1b8f3e95a1b2a8212c1a9344c344b87e86530053b.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "4d8f51640bbe42f7bdbf81cf5ebadb8c34e076434330ccb6948b6072b21254f0", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "310337d9aeb42abb9a8cb39015f1910c745c8ce5fb73c4b58ddc801c84a8bd50", "generation_seconds_batch": 24.787387477932498, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5414644479751587, "target_z": 3.3906251308998656, "ce": 6.316492557525635, "genuineness": 4.457139015197754, "identity": 0.5418785810470581, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/4d8f51640bbe42f7bdbf81cf5ebadb8c34e076434330ccb6948b6072b21254f0.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "4d9551b719f3dd0d39154cfdfd522451358791a5bf46e039deb1f9ff4d205d50", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "ad5a92c025c7540dd163bf6f9c2172b25b486482778c1505fdfafd6052a5bed3", "generation_seconds_batch": 15.898681996040978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6658473014831543, "target_z": 1.3046875144211716, "ce": 6.173524379730225, "genuineness": 4.821148872375488, "identity": 0.6975079774856567, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/4d9551b719f3dd0d39154cfdfd522451358791a5bf46e039deb1f9ff4d205d50.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "4e8f10ff2d03538df520d6a7f61de0977a4edf5c7a98d519622c5f58e7ddb6dd", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "11d9e5b2beb11e3120d030644ba929fe68b8b84e8191a8a5647ef5ed5048bf7e", "generation_seconds_batch": 17.68239559500944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20016330480575562, "target_z": 0.19531252107709698, "ce": 6.213237762451172, "genuineness": 4.770940780639648, "identity": 0.4557713270187378, "hypothesis": "Die Tür 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_Awe/4e8f10ff2d03538df520d6a7f61de0977a4edf5c7a98d519622c5f58e7ddb6dd.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "4ea7fa2f82561a42d0b65e6b56eaefbaa268465f3d65aaf2ce5e451a52c9fef5", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e061b5138a42ba8d459e0e1c32c1166f5b0c7a301d6b1f291c23dab500be75fe", "generation_seconds_batch": 23.90323074697517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23131820559501648, "target_z": 0.26953123613348884, "ce": 6.086154937744141, "genuineness": 4.381826400756836, "identity": 0.6593471765518188, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/4ea7fa2f82561a42d0b65e6b56eaefbaa268465f3d65aaf2ce5e451a52c9fef5.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "4ee0ef523353c172075953e30a1051c6b100d498a228947d2ce913d7d62c180d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c6df8e757e940ec3a4baf0c18c2cb2574621f049acd62a2df89b146071e23b7b", "generation_seconds_batch": 23.889998727012426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0626624822616577, "target_z": 2.24999987575606, "ce": 6.062326908111572, "genuineness": 4.6705241203308105, "identity": 0.7767431735992432, "hypothesis": "J'ai trouvé la 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_Awe/4ee0ef523353c172075953e30a1051c6b100d498a228947d2ce913d7d62c180d.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "4ee3d94ed6af8394f495d118d4f5a48e1cbdb696ef04c6b79ea30f3cf6e88053", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ea05aaa114822015b940db51dd23dced23f26955497c18169fbf24bdae0c38ed", "generation_seconds_batch": 18.194606133038178, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09727008640766144, "target_z": -0.04980469207594869, "ce": 6.173524379730225, "genuineness": 4.20609712600708, "identity": 0.5439363121986389, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/4ee3d94ed6af8394f495d118d4f5a48e1cbdb696ef04c6b79ea30f3cf6e88053.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": "4f09e2b440854e82e1899ccb1ba9890dcdb063a9e9a444a6c6178258ac1280d6", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "77dbec9a2d9bfc269d90b60f3ca4b155a13ad6e0c114c168a98e272b66539cef", "generation_seconds_batch": 18.14836577803362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15814515948295593, "target_z": 0.09521485824050417, "ce": 5.839932441711426, "genuineness": 4.331617832183838, "identity": 0.12578831613063812, "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_Awe/4f09e2b440854e82e1899ccb1ba9890dcdb063a9e9a444a6c6178258ac1280d6.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "4f40415d2edcc2d1fa88aa6c9f7e4fca811b7c40e904e3be48fb643ce393e81e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "270b1bbb124c19d4db53f4360310d7b6fd9288307d00a1d5c689dcc9a12ddd88", "generation_seconds_batch": 17.255804802989587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6297731995582581, "target_z": 1.2187500399355522, "ce": 6.09409761428833, "genuineness": 4.413206577301025, "identity": 0.6010586619377136, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/4f40415d2edcc2d1fa88aa6c9f7e4fca811b7c40e904e3be48fb643ce393e81e.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "5149288a55966953f0b0d558c110abc7299e8f07d238b3e6acb324a37fe3cd89", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "db865dab8cafcabbeb3617c7aa32a15cf84f9a573206bf1c7ebcff8afcd29b79", "generation_seconds_batch": 23.667781451018527, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0823392868041992, "target_z": 2.2968749134729705, "ce": 5.649308204650879, "genuineness": 3.8922953605651855, "identity": 0.14442597329616547, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/5149288a55966953f0b0d558c110abc7299e8f07d238b3e6acb324a37fe3cd89.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "51c60f1d742fd3f6335a16d78b557a2a4fb7bf7613acce4fa2d553009d190ae7", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "8496fdcf8dc27ff12cf2ce02c598bea01c87087efe68ef819e085f865d5a1cdd", "generation_seconds_batch": 21.277143208077177, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19442424178123474, "target_z": 0.18164064690908766, "ce": 6.284721851348877, "genuineness": 4.607763767242432, "identity": 0.6912330389022827, "hypothesis": "Die Tür 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_Awe/51c60f1d742fd3f6335a16d78b557a2a4fb7bf7613acce4fa2d553009d190ae7.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "51e27167afdd83fc1604c76778963fa30ab74a4b9ed7f073331ff9647c118a1e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "15a0c53268c4af13680e8a88acd40107b45ab63b09819e68aa0954e24161fed8", "generation_seconds_batch": 25.556785881053656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0626624822616577, "target_z": 2.24999987575606, "ce": 6.546830177307129, "genuineness": 4.482243061065674, "identity": 0.4839947819709778, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/51e27167afdd83fc1604c76778963fa30ab74a4b9ed7f073331ff9647c118a1e.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "5367a7111b09c2dba5c922235942a62ebd318042dd808d2c42097e7b84366551", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "7138affe9eb110a1e8da8ecad20e1eac94bed52762169bfde1964a5ba04cf51f", "generation_seconds_batch": 27.513061195029877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21738049387931824, "target_z": 0.23632814358112497, "ce": 6.006728172302246, "genuineness": 4.7834930419921875, "identity": 0.7960898876190186, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/5367a7111b09c2dba5c922235942a62ebd318042dd808d2c42097e7b84366551.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "53b3119e7ac913c0491dcf97234db6e7b73725030e5fc1ff55977f718aba9324", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fde3f4c854d2f51f55e1430fd9450129aa6012f3dc8e23416002c6a4abcbb3bc", "generation_seconds_batch": 23.36708375706803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6595251560211182, "target_z": 3.671875073215179, "ce": 6.38003396987915, "genuineness": 4.582659721374512, "identity": 0.21470798552036285, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/53b3119e7ac913c0491dcf97234db6e7b73725030e5fc1ff55977f718aba9324.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "53b3def2e7b4342882f38f3d68b572400d766b5dc50e726c95d551b5f5e3cbb6", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ebfd8f840c27aab2c2316c50ea2a0147fce769fa9367d0ca7e2571f77d4818ee", "generation_seconds_batch": 25.805361568927765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1216928958892822, "target_z": 2.390624988906791, "ce": 6.173524379730225, "genuineness": 4.65797233581543, "identity": 0.7700557112693787, "hypothesis": "J'ai trouvé la 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_Awe/53b3def2e7b4342882f38f3d68b572400d766b5dc50e726c95d551b5f5e3cbb6.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": "53f05267832021c1652bb135a940b2c65fc1827474aaefa1c26c304659ec46b9", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The keys are on the kitchen table.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cfce9d29f538ff6255d5674575bede3dc502da1cdfe8b13fdbdeced9709d02e7", "generation_seconds_batch": 17.756574998027645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7710269689559937, "target_z": 3.9375000976202386, "ce": 6.38003396987915, "genuineness": 4.519899368286133, "identity": 0.5356071591377258, "hypothesis": "The keys are on the kitchen table. I checked the drawer. Then look beside the window. Take them with you when you leave.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/53f05267832021c1652bb135a940b2c65fc1827474aaefa1c26c304659ec46b9.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "541e7a25a866bbbe78b95765514d044527e53937d07793095ebcd23c494f736c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7fd4d046a056a1d649739a927a2589aae73c368ee01f63139a0f572ee1ab8150", "generation_seconds_batch": 22.9868031720398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1676054000854492, "target_z": 2.499999982250866, "ce": 6.284721851348877, "genuineness": 4.570107460021973, "identity": 0.5379078388214111, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/541e7a25a866bbbe78b95765514d044527e53937d07793095ebcd23c494f736c.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "23a0800840ae543367b80254c7a84e6477fa6ae5a9543bd92533914eb7e93186", "generation_seconds_batch": 18.441255001933314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.070624440908432, "target_z": -0.1132812405707724, "ce": 6.308549880981445, "genuineness": 3.7667744159698486, "identity": 0.5924103260040283, "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_Awe/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "546b17da35b091833fecdee322b9f227db197f7cd23095c260a759d8a15477a4", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6d8a65b3cbb58461ab3b681a2e0b5f993a2de726e08ae3c59ac5a03051e8c2e2", "generation_seconds_batch": 27.968990375986323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.590419590473175, "target_z": 1.1249999645017315, "ce": 6.229123115539551, "genuineness": 4.425758361816406, "identity": 0.6303502321243286, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/546b17da35b091833fecdee322b9f227db197f7cd23095c260a759d8a15477a4.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "549ca0779d46158bd3417204b86de72f4f5f2bf69dc9b5a831dd1239e4d4f0d9", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "eca7ce59a56f898795b542d0c7abf6c3f5d93830df0a3b9740b5fadaed618297", "generation_seconds_batch": 26.508791313972324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7511134147644043, "target_z": 1.507812583199067, "ce": 5.784333229064941, "genuineness": 4.632867813110352, "identity": 0.6408947706222534, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/549ca0779d46158bd3417204b86de72f4f5f2bf69dc9b5a831dd1239e4d4f0d9.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "54e0df099c082826b9d8ce2f9e6707cd593ae87d07c7056c92819e0deca74b62", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e92ad1743081782c3efd92fb1d4908a1de48e102235444b914b982064be8971d", "generation_seconds_batch": 16.889168279012665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.273131400346756, "target_z": 0.3691406557836548, "ce": 5.77639102935791, "genuineness": 4.570107460021973, "identity": 0.739138126373291, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/54e0df099c082826b9d8ce2f9e6707cd593ae87d07c7056c92819e0deca74b62.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "5594ed0365cd66317e400235717a6a5e13869d4299c845e91d6b8bd0a43755dc", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "cb5110b9f9500f9e744457b921b210abc07dd50789d1ecd305274f6b05f08b93", "generation_seconds_batch": 22.677206362015568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3119019269943237, "target_z": 2.8437501641794922, "ce": 6.300607204437256, "genuineness": 4.557555198669434, "identity": 0.5006743669509888, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/5594ed0365cd66317e400235717a6a5e13869d4299c845e91d6b8bd0a43755dc.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "56137f4ba13a88386142fac007e666d7484e6898db5da844dcad308750a70fc8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f099069e2fb784432aa5540da5102c6bd2beaafa596f5b7394f9ba83b54a6323", "generation_seconds_batch": 22.901676808018237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.813423216342926, "target_z": 1.6562500133118507, "ce": 6.229123115539551, "genuineness": 4.356721878051758, "identity": 0.7351928949356079, "hypothesis": "J'ai trouvé la 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_Awe/56137f4ba13a88386142fac007e666d7484e6898db5da844dcad308750a70fc8.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "563de05eff4c4abd2ecd7b4a702d086fb608e1f3289f3383ddbd06429f0e37a4", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2f043bace987b6057d775ab4f69fbef2c27ebe1f6a35071da366f305195f9052", "generation_seconds_batch": 17.527516140020452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07923303544521332, "target_z": -0.09277342931875841, "ce": 6.268836498260498, "genuineness": 4.519899368286133, "identity": 0.544926643371582, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/563de05eff4c4abd2ecd7b4a702d086fb608e1f3289f3383ddbd06429f0e37a4.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "57089ef53eabae8d9e86c1e328e14a97063e9a1eba29a0b783c580ea550f7533", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b66fc7df69ffa12c78ae38e85e5b25460b13fd53d0b26e5005b283989dad6cee", "generation_seconds_batch": 23.57557928597089, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14625708758831024, "target_z": 0.06689451703682604, "ce": 6.300607204437256, "genuineness": 4.570107460021973, "identity": 0.6251285672187805, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/57089ef53eabae8d9e86c1e328e14a97063e9a1eba29a0b783c580ea550f7533.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "570c4c2f450f033a5fc3937fb9aee1a9fad7aecd86d8f463c7a2a9a6ba65e35e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "bd8ddd4a488cb6da6842feec9577dff2a94ccdb2e93a0652c7e5e9b11fb49bef", "generation_seconds_batch": 18.349288161029108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4887561798095703, "target_z": 0.8828124589551269, "ce": 6.0305562019348145, "genuineness": 3.7416701316833496, "identity": 0.4250796139240265, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/570c4c2f450f033a5fc3937fb9aee1a9fad7aecd86d8f463c7a2a9a6ba65e35e.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": "57612f0911766918ee907799d50dc62535633d26f9d876f97c9217daee39110f", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "138119d31421a000312590cab53c5196aec6d4e45dcd1bd9976b404aed6e87bb", "generation_seconds_batch": 23.860637701000087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1923745572566986, "target_z": 0.1767577890655961, "ce": 6.2767791748046875, "genuineness": 4.482243061065674, "identity": 0.6064030528068542, "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_Awe/57612f0911766918ee907799d50dc62535633d26f9d876f97c9217daee39110f.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "5774f85add74c7ee0de3c6b1dcbada7d62d24bda81a59394d7b639f692bda57f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ac93c24b919cb60233dcbc18ab5062f6aa44c716b3cc665b1b571dbfbd65504b", "generation_seconds_batch": 25.128766463021748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26247313618659973, "target_z": 0.34375002218641787, "ce": 5.824047088623047, "genuineness": 4.3127899169921875, "identity": 0.6492077112197876, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/5774f85add74c7ee0de3c6b1dcbada7d62d24bda81a59394d7b639f692bda57f.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "58674d8f75f7006171419040a58f91cfa949038526ac5d9d0fb638f851537aff", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "18761ea640ade1aa8b3757f9de3eb83fe3257f0f746c345a0454ade07993d8ba", "generation_seconds_batch": 23.471134782070294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8298205733299255, "target_z": 1.6953125920736343, "ce": 6.23706579208374, "genuineness": 4.645420074462891, "identity": 0.8143761157989502, "hypothesis": "J'ai trouvé la 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_Awe/58674d8f75f7006171419040a58f91cfa949038526ac5d9d0fb638f851537aff.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "587791bf1196b2604d97385728eff2ed2b7718f9305d2a762607366047de565e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a6a7de2aabe577448b0cf1ad5c895a1e7750b2a227725edbc2419d1f329f690d", "generation_seconds_batch": 22.322407337022014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23623740673065186, "target_z": 0.2812499955627164, "ce": 5.95112943649292, "genuineness": 4.3127899169921875, "identity": 0.599098265171051, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/587791bf1196b2604d97385728eff2ed2b7718f9305d2a762607366047de565e.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "58d8f47bf1b8cdd785b4e5c086c55b086567a5102c4b8ba92abd0a540895efdc", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f27de16ab86b1d39d2848f539442b32b794a02f71023e3c12b055296351a3671", "generation_seconds_batch": 25.438535648048855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05668671056628227, "target_z": -0.146484377495972, "ce": 6.062326908111572, "genuineness": 4.582659721374512, "identity": 0.7162246704101562, "hypothesis": "De dator 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_Awe/58d8f47bf1b8cdd785b4e5c086c55b086567a5102c4b8ba92abd0a540895efdc.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "595424a52491f038b637bb0a94566fd97705f2ffa1321dddf3fc626677ddc6ce", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "94a1be8ddcf7014efacc91ecf5da28cfb513808a670fb4595022c8fa7a004c53", "generation_seconds_batch": 21.916048810933717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.138673335313797, "target_z": 0.04882813470655782, "ce": 6.260893821716309, "genuineness": 4.482243061065674, "identity": 0.7998098134994507, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/595424a52491f038b637bb0a94566fd97705f2ffa1321dddf3fc626677ddc6ce.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "5a04a8f52668525db9f23e169cee56f4ad285848546d4316d546eec477a6122e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0c0653b6ba10d1ef5c1347dd7fe8d27f7156c847a3d1194f4e72d8fd77d31521", "generation_seconds_batch": 21.65055093902629, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5414644479751587, "target_z": 3.3906251308998656, "ce": 6.054384231567383, "genuineness": 4.432034492492676, "identity": 0.5296805500984192, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/5a04a8f52668525db9f23e169cee56f4ad285848546d4316d546eec477a6122e.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "5a0f31c71f2e1c83565faa82f0238a0c52d4189138e83b54f0441ec5b638078b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "654e4b2bf955a37c0cfd31eaa2cf8170bdc023cc49dd009de1d251cdfe9e0dcb", "generation_seconds_batch": 23.64021608699113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11038795113563538, "target_z": -0.01855467876409796, "ce": 5.967014789581299, "genuineness": 4.545003414154053, "identity": 0.5458531379699707, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/5a0f31c71f2e1c83565faa82f0238a0c52d4189138e83b54f0441ec5b638078b.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": "5a206f0bebacd4437749bd0064696f097227649161f73a81f7e0f256d34eb94f", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b3d2a840cd0244dc9df75345319ac19abfd039631b2d7727dea20797fbb223e7", "generation_seconds_batch": 17.25504364608787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6068169474601746, "target_z": 1.1640625432635148, "ce": 6.252951145172119, "genuineness": 4.325342178344727, "identity": 0.49199122190475464, "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_Awe/5a206f0bebacd4437749bd0064696f097227649161f73a81f7e0f256d34eb94f.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": "5b276ca61fa689fc8bb113d6ff38d0182835f2717c2f1c06e13efc9ff12efbf1", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9989d14c1e55d608e293341d697e0c8ae2b042387b125caabc3d49cfe485ec58", "generation_seconds_batch": 15.5789674409898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6136126518249512, "target_z": 3.5625000798711044, "ce": 5.696964263916016, "genuineness": 4.281409740447998, "identity": 0.4523409605026245, "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_Awe/5b276ca61fa689fc8bb113d6ff38d0182835f2717c2f1c06e13efc9ff12efbf1.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "5b85dc530ce8ac846eb73a4299d721e681c833e3dc3846f9526e6b2c3c7104dd", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7bdfabd5f574b2af2a904723ea42fda8dc2e4d1a5b9793e8a8ad7dff33cb3c89", "generation_seconds_batch": 23.197548842057586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2477155327796936, "target_z": 0.30859374389873506, "ce": 6.109982967376709, "genuineness": 4.557555198669434, "identity": 0.4400007724761963, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/5b85dc530ce8ac846eb73a4299d721e681c833e3dc3846f9526e6b2c3c7104dd.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "5bc12424676eb88419c55bd010d73a10e15873dec2a0315250d31e17b29f4d5f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "5543922292a624f7abaa422cd61cb32e74e637f1506509a3f765503911a0b99c", "generation_seconds_batch": 22.67648267291952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1938410997390747, "target_z": 2.5624999378780298, "ce": 5.95112943649292, "genuineness": 4.18726921081543, "identity": 0.3186706602573395, "hypothesis": "The 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_Awe/5bc12424676eb88419c55bd010d73a10e15873dec2a0315250d31e17b29f4d5f.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": "5bf05395a6ae2575dfd935fa58c8c3f33fbf778546246bdf676d70f5b2243dd5", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "292322ffe749789352c4daa5e2890993ef396cb3b30af26cc2f72828bd7047d2", "generation_seconds_batch": 18.318146887002513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04930791258811951, "target_z": -0.16406250776524625, "ce": 6.205295085906982, "genuineness": 4.532451152801514, "identity": 0.6874687671661377, "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_Awe/5bf05395a6ae2575dfd935fa58c8c3f33fbf778546246bdf676d70f5b2243dd5.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "5c3fe451a60e2ae51d5b4e719c8a291d8aeeb5fb05f71fbb87b044bf577024f1", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9f8f27be8bd24784bedfda57c98c50e3ae760fc13bc1cd0f6217ca7300170511", "generation_seconds_batch": 25.760857818066142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5346686840057373, "target_z": 0.9921874522992016, "ce": 6.181467056274414, "genuineness": 4.432034492492676, "identity": 0.5898436307907104, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/5c3fe451a60e2ae51d5b4e719c8a291d8aeeb5fb05f71fbb87b044bf577024f1.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": "5d9ca83302b080ac4dd3392af57481bf3497aa744f966b79af003805e5eef074", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Your message arrived after I had left.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4ff3db833722a16fbfe7cf5f3dd7670ca00300d5f4a5aefce6311ddc98315543", "generation_seconds_batch": 17.85030231496785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39529144763946533, "target_z": 0.6601562427894142, "ce": 6.395919322967529, "genuineness": 4.331617832183838, "identity": 0.27959123253822327, "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_Awe/5d9ca83302b080ac4dd3392af57481bf3497aa744f966b79af003805e5eef074.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "5de046dcca477144cc96e674aa956f3040ef918628956bd97f140be0b9e95647", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "e0cd3a38f53dcabed9256a862be8a253d8b28feaaa67b8bd0f5fe91676164679", "generation_seconds_batch": 23.737578265951015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19278450310230255, "target_z": 0.17773438193325558, "ce": 6.221180438995361, "genuineness": 4.770940780639648, "identity": 0.624995231628418, "hypothesis": "Die Tür 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_Awe/5de046dcca477144cc96e674aa956f3040ef918628956bd97f140be0b9e95647.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "0123fd4fd0e50273c7154ba9c1e0317ecbed2ff3a85de868e05dc5a4c6fcf54f", "generation_seconds_batch": 18.96747257001698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10792835056781769, "target_z": -0.02441405847871176, "ce": 6.046441555023193, "genuineness": 4.432034492492676, "identity": 0.792863667011261, "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_Awe/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.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": "5ebde35e3c92a9c790659fcc3776b188467b04338a72dc3199d627f232201652", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Escribí el número en el sobre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0e8bb41cd1bcdb37c807ff509769acce9105b15bd1924b91553dc49b9f0720e0", "generation_seconds_batch": 23.364312798017636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1413697004318237, "target_z": 2.4375000266237015, "ce": 6.09409761428833, "genuineness": 4.419482707977295, "identity": 0.4458584785461426, "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_Awe/5ebde35e3c92a9c790659fcc3776b188467b04338a72dc3199d627f232201652.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "5edd74646d4d24c9c3e478323795374e28e99cfa7f8f4051892cd3198f06c751", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "adf69a61a9c051cf0388aaab98e60ad7a4c8124805975c0796674feea478646d", "generation_seconds_batch": 27.920442400034517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9118071794509888, "target_z": 1.8906250599033283, "ce": 6.157639026641846, "genuineness": 4.281409740447998, "identity": 0.5749598145484924, "hypothesis": "J'ai trouvé la 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_Awe/5edd74646d4d24c9c3e478323795374e28e99cfa7f8f4051892cd3198f06c751.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "5eeca66732c70552019728fd93ea435944614c7a0e6779f8babab3e268c6a1f1", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "efa68f8c808dfef68642a3ba0755195e1441fa67de97a2c9f6baff38d08e0d72", "generation_seconds_batch": 18.58682055491954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7314366102218628, "target_z": 1.4609375454821567, "ce": 6.443574905395508, "genuineness": 4.482243061065674, "identity": 0.5376379489898682, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/5eeca66732c70552019728fd93ea435944614c7a0e6779f8babab3e268c6a1f1.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "5f084651b4eec5bee3a64bce99d58f10de5e4b70841afd15635e92c83fe79b40", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "aefa3f2d04c46b24970d325b48a2e8ad6ab4c5a30e86154acb36ee01c34dc467", "generation_seconds_batch": 24.210201211972162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6724062561988831, "target_z": 1.3203125743244999, "ce": 6.332377910614014, "genuineness": 4.381826400756836, "identity": 0.5688623189926147, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/5f084651b4eec5bee3a64bce99d58f10de5e4b70841afd15635e92c83fe79b40.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "5f694fb4065ac21303ff3b623b3b7e75d97f577993c0ebf135239d64f32d8b83", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "82f8c7ebb9f5e5bb85cd70f38a2b13087f3677c857ec1cea7a10ac7662fdc098", "generation_seconds_batch": 24.034011828014627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4625204801559448, "target_z": 0.8203125033279627, "ce": 5.927301406860352, "genuineness": 4.432034492492676, "identity": 0.38109222054481506, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/5f694fb4065ac21303ff3b623b3b7e75d97f577993c0ebf135239d64f32d8b83.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "5f798722d6328ee694adf73168229b7ad504dda2b512c671c881b368408a696f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "123516a87f54e77959aac04061a58c16a1b21ceada9ba729476e3c7da9edf2c1", "generation_seconds_batch": 25.057579408050515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8855714797973633, "target_z": 1.828125104276164, "ce": 6.2767791748046875, "genuineness": 4.68307638168335, "identity": 0.795785665512085, "hypothesis": "J'ai trouvé la 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_Awe/5f798722d6328ee694adf73168229b7ad504dda2b512c671c881b368408a696f.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "5f9100fc721940a0364f1a9bbf72ef32e0bc3db4cc754012d930c253c31fb385", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b5de775ce218389f5209d331f58b67bd3efdb0bd36e17075c9b1708460816a1a", "generation_seconds_batch": 20.0765842969995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5510660409927368, "target_z": 1.0312500310609851, "ce": 6.181467056274414, "genuineness": 4.6705241203308105, "identity": 0.6911095976829529, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/5f9100fc721940a0364f1a9bbf72ef32e0bc3db4cc754012d930c253c31fb385.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "5fe38bd690c193c00f078b8737de6158c2d6c80ef165771a5490e622d4ba2b16", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "51e1e92f85f4cc7c34de1c0c36452365f98ba0cb2c642ae21d313ebb7b5fee14", "generation_seconds_batch": 22.9868031720398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2135179042816162, "target_z": 2.6093749755949402, "ce": 6.292664527893066, "genuineness": 4.846253395080566, "identity": 0.6748734712600708, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/5fe38bd690c193c00f078b8737de6158c2d6c80ef165771a5490e622d4ba2b16.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "60163b406dba70cb29a29be44a383e8b29c05290e2ee91e8cbbf775a28ab52f4", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2962d34a28f9f247bff588df425b65d896fde443bd04a09d5b4b97f968c7c953", "generation_seconds_batch": 16.581624803016894, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6658473014831543, "target_z": 1.3046875144211716, "ce": 6.054384231567383, "genuineness": 4.15588903427124, "identity": 0.6109763979911804, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/60163b406dba70cb29a29be44a383e8b29c05290e2ee91e8cbbf775a28ab52f4.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "60632e8673276abbc04e56fb62dd6ea934d4106472b8bc4270c1c9185d49aea9", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "815ce45e8dd3ac7064065c1c5eafd4e5db2c769314a47752dc4f62a50e349a40", "generation_seconds_batch": 23.025749254971743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8234983682632446, "target_z": 4.062500008874567, "ce": 6.38003396987915, "genuineness": 4.532451152801514, "identity": 0.5113980770111084, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/60632e8673276abbc04e56fb62dd6ea934d4106472b8bc4270c1c9185d49aea9.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "606b0789287d146673cc7de6df94d218b4bf027819609f17edfcc45d9c98a144", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8aaf348051000a1e1e46b9402662c4d0a87f9d226009416397537f845faf2b32", "generation_seconds_batch": 18.69190172094386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13211439549922943, "target_z": 0.033203110301498154, "ce": 6.062326908111572, "genuineness": 4.432034492492676, "identity": 0.8009907603263855, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/606b0789287d146673cc7de6df94d218b4bf027819609f17edfcc45d9c98a144.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "6189302bc28b7a776cb42c4b0818f6c0cb2c9026a3090113f71e88686dbba225", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c8e2cb656a325dbc81c5e6f8c7119cc467df9163de0c48bb5169068f048aff63", "generation_seconds_batch": 25.760857818066142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4707191288471222, "target_z": 0.8398437217123172, "ce": 6.1894097328186035, "genuineness": 4.419482707977295, "identity": 0.27556249499320984, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/6189302bc28b7a776cb42c4b0818f6c0cb2c9026a3090113f71e88686dbba225.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "61a6cc3f990b9140abf2921181e7457d52d501174b658f68fab2d8b6193faf1a", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2035f4e3c1a2848df83665601a19051a25270a11806e7f182f95872ee22af776", "generation_seconds_batch": 19.376216926961206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8234983682632446, "target_z": 4.062500008874567, "ce": 6.467403411865234, "genuineness": 4.582659721374512, "identity": 0.40070444345474243, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/61a6cc3f990b9140abf2921181e7457d52d501174b658f68fab2d8b6193faf1a.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "61ba1551282ebef529d9767d647eefa2ae25a94beef4eb372f5f1b9a8ee503c1", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a5e71f570249ef5b18499f2b790f2c25bc6de279cafc95603aad367e0b698452", "generation_seconds_batch": 17.77762654691469, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07472376525402069, "target_z": -0.10351563137859514, "ce": 6.038498878479004, "genuineness": 4.8588056564331055, "identity": 0.8545195460319519, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/61ba1551282ebef529d9767d647eefa2ae25a94beef4eb372f5f1b9a8ee503c1.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "61bebdc0b14e4f1f9358a0293e864d76ad89959e7597726a485ee9eb506df0c0", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a2a838b5e33bac0c0d15f315d5c4dfb80bca707b0c95a4e6a0c5808d663c6b33", "generation_seconds_batch": 16.37060394603759, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.243269920349121, "target_z": 5.062500150867642, "ce": 6.165581703186035, "genuineness": 4.720732688903809, "identity": 0.5620940327644348, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/61bebdc0b14e4f1f9358a0293e864d76ad89959e7597726a485ee9eb506df0c0.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "61f371c272cdb2a15b7b7fef99b8008a754871540e052870e359e7544194705d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8479108b9e844d867dab862b4203dbcd2b65c19ef205150baa4c951556b9bfa5", "generation_seconds_batch": 22.526593195972964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6888035535812378, "target_z": 1.359375011093209, "ce": 5.839932441711426, "genuineness": 4.444586753845215, "identity": -0.08149407058954239, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/61f371c272cdb2a15b7b7fef99b8008a754871540e052870e359e7544194705d.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "622d4c655871766969064c7a96cb08413363b374f6f6d07f76f829316c7858ea", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bada339f368f785aba30459b0780cbca5aece05bf2d6a7679cc96571611dbdf6", "generation_seconds_batch": 22.995427452027798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8265410661697388, "target_z": 1.687499991125433, "ce": 5.418970584869385, "genuineness": 4.13078498840332, "identity": 0.532479465007782, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/622d4c655871766969064c7a96cb08413363b374f6f6d07f76f829316c7858ea.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "6235927b01897f6c8dd0b8629637fc8753d10e1499f31c9a663c4ccb6df7c0d6", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "70888124b096a6218dc95ac70ace2126b038da5c12b7db5aa0fb1d9aec7667ae", "generation_seconds_batch": 23.87535902496893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.060376107692718506, "target_z": -0.13769531679861846, "ce": 6.1020402908325195, "genuineness": 4.494794845581055, "identity": 0.7990597486495972, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/6235927b01897f6c8dd0b8629637fc8753d10e1499f31c9a663c4ccb6df7c0d6.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "62373dbf60ec82583f98ebcb0b45e6e0b2a4fea5922202ca5e52bbac2c740a7e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "abb1b9c85627da178dfdbbbacd921da5487234533b241ccce73a481b099dc248", "generation_seconds_batch": 23.025749254971743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6267304420471191, "target_z": 3.593749915691612, "ce": 6.221180438995361, "genuineness": 4.507347106933594, "identity": 0.3311486840248108, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/62373dbf60ec82583f98ebcb0b45e6e0b2a4fea5922202ca5e52bbac2c740a7e.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "628194ab296210c90a0a67269797590f897ea31b3ef213417f24994b1797b797", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "02e97ab11c39ffda03f9c276eb2d28c19b6e4563d39ee1a8e79b6d62fb199d89", "generation_seconds_batch": 24.1981374330353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7710269689559937, "target_z": 3.9375000976202386, "ce": 6.395919322967529, "genuineness": 4.758388519287109, "identity": 0.4192492365837097, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/628194ab296210c90a0a67269797590f897ea31b3ef213417f24994b1797b797.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": "62a09dccfaf783cefac2f6005a573820b51e5b2f733174641232f73c06c031dc", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6b89dea669382298194593e9b78d61c3efae2133bc927f92c3d7d0658e4a2f5c", "generation_seconds_batch": 23.75709748698864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0101910829544067, "target_z": 2.1249999645017312, "ce": 6.316492557525635, "genuineness": 4.331617832183838, "identity": 0.6607547402381897, "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_Awe/62a09dccfaf783cefac2f6005a573820b51e5b2f733174641232f73c06c031dc.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "62de74db01ec1de1a8dca6ec3692e5bc512cf2e5cad0ca3cfa6426794f1ecf96", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "42daa1bac8a6b7b3e09fd31bb73b56092072c2375de087fa7100d0bc6f688282", "generation_seconds_batch": 24.31377963605337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06324563920497894, "target_z": -0.1308593797146138, "ce": 6.173524379730225, "genuineness": 4.507347106933594, "identity": 0.8012672662734985, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/62de74db01ec1de1a8dca6ec3692e5bc512cf2e5cad0ca3cfa6426794f1ecf96.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "62e3bd22dc05ae18461ebef938ed2011ea24f2f5be97bdd3c30f07b819219cc0", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8237d8f16906eb43102f68d6d10d7d2e8a5dff09a8c0d69cd43430aea9282641", "generation_seconds_batch": 27.06583886197768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15978488326072693, "target_z": 0.09912108771806764, "ce": 6.054384231567383, "genuineness": 4.457139015197754, "identity": 0.5408257246017456, "hypothesis": "La puerta sigue abierta. he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/62e3bd22dc05ae18461ebef938ed2011ea24f2f5be97bdd3c30f07b819219cc0.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "630322576cca4be7c9a1a1be9b3c6e149b92874eba85e33acadabe695d53eaa3", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "dc0c3a580ebb9de8f28a72ce05412172280d882acb1e35bd26f34105a98cf28d", "generation_seconds_batch": 21.65055093902629, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5480233430862427, "target_z": 3.4062500488101195, "ce": 5.919358730316162, "genuineness": 4.720732688903809, "identity": 0.49954646825790405, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/630322576cca4be7c9a1a1be9b3c6e149b92874eba85e33acadabe695d53eaa3.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "635fc49ed311c50519f7f9486e00b24437673b2a8debca1d36e21414ad645f69", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "dc76c6c4a1525bf510081cb96aadb251cb13b5140f254d60f694f124741c0516", "generation_seconds_batch": 17.179644610965624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3608570694923401, "target_z": 0.5781249977813582, "ce": 6.1020402908325195, "genuineness": 4.595211505889893, "identity": 0.6346710324287415, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/635fc49ed311c50519f7f9486e00b24437673b2a8debca1d36e21414ad645f69.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "63722cd3b3e6dc1e7874ee502b7ed6faff1e03f5d070ebeda7ff8b057da18799", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a1662f1009238f0577bdacec4c14b48909daf46aa78cb29cc7299d7e312ab932", "generation_seconds_batch": 20.721013133064844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5873769521713257, "target_z": 3.50000012424394, "ce": 6.086154937744141, "genuineness": 4.168440818786621, "identity": 0.36609771847724915, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/63722cd3b3e6dc1e7874ee502b7ed6faff1e03f5d070ebeda7ff8b057da18799.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "63bb5459361db5f34ced5fe87711da6dd5f37565f3d948cfc6aa8ad159ba8f5d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0d1fa2430a123228c54e4daa7f658c87900f40f06b55749adf896aa09df43d6a", "generation_seconds_batch": 17.217161747976206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8759697675704956, "target_z": 4.187499920128896, "ce": 6.356205940246582, "genuineness": 4.532451152801514, "identity": 0.4422590732574463, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/63bb5459361db5f34ced5fe87711da6dd5f37565f3d948cfc6aa8ad159ba8f5d.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "63c0a1cac4eea40bd9fb50a9c69c50fabd4c62a5b2c09e212c607e4c14dc3989", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "dbe56505c1ca8e88fa2eb1260eb961f2c0f38f0aa6bd03dfa03b176d0d4ba0c1", "generation_seconds_batch": 28.007033691974357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4887561798095703, "target_z": 0.8828124589551269, "ce": 5.760505676269531, "genuineness": 4.7458367347717285, "identity": 0.5358712077140808, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/63c0a1cac4eea40bd9fb50a9c69c50fabd4c62a5b2c09e212c607e4c14dc3989.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "63ed309d16db8ca85413b148ea0a5f13e41f79f929fdc66dc2933af2446b05a4", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9dabeca7808b6434968bf11e29a2be54e1fd6e5d2310c037720c3b098738cf84", "generation_seconds_batch": 24.57433576998301, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5051535367965698, "target_z": 0.9218750377169104, "ce": 6.507116317749023, "genuineness": 4.457139015197754, "identity": 0.6120889782905579, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/63ed309d16db8ca85413b148ea0a5f13e41f79f929fdc66dc2933af2446b05a4.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "64835b266aeb820afd84205b8120d2b0430e7c32282fe8d59b803ab4db018462", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7e4ab18a35dd968431aaea26f3fd6b16a1ac8c73a0f0c007d2ca9c6613c8e082", "generation_seconds_batch": 24.36152337503154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0233089923858643, "target_z": 2.156250084308388, "ce": 6.300607204437256, "genuineness": 4.582659721374512, "identity": 0.7499915361404419, "hypothesis": "J'ai trouvé la 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_Awe/64835b266aeb820afd84205b8120d2b0430e7c32282fe8d59b803ab4db018462.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "6489e90d1bd853594353df07f1199baa10726ed75d6c16bf23f9914d6ed3bb32", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "06f2bb103280cad4107949c3b68f2957ea7a5c45869edc0530ba5b76864c9a16", "generation_seconds_batch": 23.112113401060924, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0036321878433228, "target_z": 2.1093750465914773, "ce": 6.435632705688477, "genuineness": 4.557555198669434, "identity": 0.4386281371116638, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/6489e90d1bd853594353df07f1199baa10726ed75d6c16bf23f9914d6ed3bb32.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "64fc59bd8a550394a747178571da07a4a7128d787ce2777b47e839ef1ea7be5c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "fcc706026f1d31634018775635fe3ae163c08e1dcf4773380d8067821c37d58d", "generation_seconds_batch": 17.548447089036927, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3608570694923401, "target_z": 0.5781249977813582, "ce": 6.316492557525635, "genuineness": 4.356721878051758, "identity": 0.5950433015823364, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/64fc59bd8a550394a747178571da07a4a7128d787ce2777b47e839ef1ea7be5c.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "650cb306c6a0f5e6b6d388d3cbbf91f21205b9aabd5960612ba756e9a8e2671d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "59f740500af2c4742f74752a2ac7a2e74a6cbd397078c805c27e5b9eb8201fb5", "generation_seconds_batch": 22.901676808018237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49859458208084106, "target_z": 0.9062499778135821, "ce": 6.022613525390625, "genuineness": 4.7834930419921875, "identity": 0.7111794352531433, "hypothesis": "J'ai trouvé la 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_Awe/650cb306c6a0f5e6b6d388d3cbbf91f21205b9aabd5960612ba756e9a8e2671d.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "65154d68a88af509a15b734ee346f1bd500e7f17112d213692864c395f6fdf58", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "13a1eb9c6f0968a4a622fd8795c8e46fe80ffca942a5dc003532145df8ea7c11", "generation_seconds_batch": 32.32070487795863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1020160913467407, "target_z": 2.3437499511898805, "ce": 6.38797664642334, "genuineness": 4.632867813110352, "identity": 0.6097252368927002, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/65154d68a88af509a15b734ee346f1bd500e7f17112d213692864c395f6fdf58.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "655b29439cc5bee42fae810679a7fa44946657aaafb9357a298934d5cefa709e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "384ce3fcc2257118ddae885cfd3d6e46a53f0e55f50a29e8d428bcb0ca98fb17", "generation_seconds_batch": 24.047943711979315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07554363459348679, "target_z": -0.1015624988906791, "ce": 6.356205940246582, "genuineness": 4.293961524963379, "identity": 0.5935307145118713, "hypothesis": "Die Tür ist noch offen. Ich habe dein Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/655b29439cc5bee42fae810679a7fa44946657aaafb9357a298934d5cefa709e.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "65a1cb9b3b65fa470ea48aad442140a1391668170ad2f9c9a4631c9168d01a30", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "48703ce9b938a0564885714b6830ab41b2f1a5b4550d25fece013bb8e9c0d937", "generation_seconds_batch": 24.31377963605337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9577196836471558, "target_z": 2.000000053247403, "ce": 6.197352409362793, "genuineness": 4.632867813110352, "identity": 0.6612255573272705, "hypothesis": "De deuren deur staat nog open. Ik heb je de jasjas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/65a1cb9b3b65fa470ea48aad442140a1391668170ad2f9c9a4631c9168d01a30.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "65ea2e17af2a30aa771742fa4345adcb221af5084b74c63d6848c536bb7e6db3", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f2291552676375fd6f76630af39eeddb9a73eefa474d1dc64db9e15f9f2c1baf", "generation_seconds_batch": 24.86532627500128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.125209093093872, "target_z": 4.781249924566179, "ce": 5.871703147888184, "genuineness": 4.281409740447998, "identity": 0.43643784523010254, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/65ea2e17af2a30aa771742fa4345adcb221af5084b74c63d6848c536bb7e6db3.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": "662222299da44e59b5c5cc36bc9dfd5fd4fa66041bf6d7e2c05ac184824fe14f", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I wrote the number on the envelope.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "325d5af00e8d9e1810e766910808dcff9adac0f7403fa082f71d9d641830a9f3", "generation_seconds_batch": 17.154403944965452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28133004903793335, "target_z": 0.38867187416800936, "ce": 6.2767791748046875, "genuineness": 4.18099308013916, "identity": 0.4002740979194641, "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_Awe/662222299da44e59b5c5cc36bc9dfd5fd4fa66041bf6d7e2c05ac184824fe14f.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "6624c9996f929711058deba658a534e2d20a18eea475f4ece031cd611f7d6a47", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3475a025747182546cdbce0ace67a1510ec47245d258d68cba4d5943b1f501f0", "generation_seconds_batch": 27.429494134965353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9642786383628845, "target_z": 2.015625113150731, "ce": 6.252951145172119, "genuineness": 4.268857479095459, "identity": 0.6300186514854431, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/6624c9996f929711058deba658a534e2d20a18eea475f4ece031cd611f7d6a47.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "66920d16323b98af2bd7fbd4ec4f66a72fcb1938be4ead93251ac6f9a7266aa5", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2bb0d8e58c83e2c7c4b8351477555d022a261df896d59647fb8a85519cb965d2", "generation_seconds_batch": 23.16549112193752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5611412525177002, "target_z": 3.437500168616776, "ce": 6.443574905395508, "genuineness": 4.570107460021973, "identity": 0.4295458495616913, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/66920d16323b98af2bd7fbd4ec4f66a72fcb1938be4ead93251ac6f9a7266aa5.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "66c768596f53433fb332bd12f286c22c0404eeec13da6ba956e0c6a10b6b16c4", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f8054320d6057a296e64c50c4a3b2eac8766c8fc67e214aadd127109aa1fde00", "generation_seconds_batch": 22.382551705930382, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.140313059091568, "target_z": 0.052734364184121287, "ce": 6.24500846862793, "genuineness": 4.469690799713135, "identity": 0.650951623916626, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/66c768596f53433fb332bd12f286c22c0404eeec13da6ba956e0c6a10b6b16c4.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "66d71ffadef123f5e036ccdc278194a2ee4d6358ce299abae3a52d611dc53977", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "76384e2b33ae8ce142e21b4df0d394aca22fc96b42cb6d33fb8c0645a6999c23", "generation_seconds_batch": 23.062302823062055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9708375334739685, "target_z": 2.031250031060985, "ce": 6.173524379730225, "genuineness": 4.607763767242432, "identity": 0.7401214838027954, "hypothesis": "J'ai trouvé la 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_Awe/66d71ffadef123f5e036ccdc278194a2ee4d6358ce299abae3a52d611dc53977.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "66e8726bdcd46e0741847f9e34879b4f46d3f8683a65644aeb93629c1880df48", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "616042a97623ef8178443670a9bf53bfd5b6f0d3760449accc1ece091f4cad29", "generation_seconds_batch": 18.862459311960265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8331000208854675, "target_z": 1.7031250510287612, "ce": 6.054384231567383, "genuineness": 4.65797233581543, "identity": 0.7385151386260986, "hypothesis": "J'ai trouvé la 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_Awe/66e8726bdcd46e0741847f9e34879b4f46d3f8683a65644aeb93629c1880df48.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "66eaa3495393d226d517e3d220445f4db97ea97bfa2f8f966741d5a913ca46c2", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3132d3ad9f808b75514537ba1da71c661f9e288c5271668fba5d38fb65086e11", "generation_seconds_batch": 18.024529370944947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1663438081741333, "target_z": 0.1147460766248587, "ce": 6.1894097328186035, "genuineness": 4.68307638168335, "identity": 0.592772901058197, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/66eaa3495393d226d517e3d220445f4db97ea97bfa2f8f966741d5a913ca46c2.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "6737802e2c72a24c551a2dcaedd7f5f787f1a572acfe04d3733675ec782f8e5a", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2a91871a90c310cfa57de0306d591ceae94d5e552aecba7a11335ef4385d72f6", "generation_seconds_batch": 24.045497406972572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2856661081314087, "target_z": 2.781249924566179, "ce": 5.816103935241699, "genuineness": 4.3504462242126465, "identity": 0.23822835087776184, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/6737802e2c72a24c551a2dcaedd7f5f787f1a572acfe04d3733675ec782f8e5a.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "673ea7a0e38872c7a4583151f076f8b45e5df628cf41244bd3e3ba5871c9f039", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "237fee12693fa477691e3e432dc78e17a9345d7a599f9e46e785fafc5be99030", "generation_seconds_batch": 20.721013133064844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28051018714904785, "target_z": 0.3867187594292276, "ce": 6.252951145172119, "genuineness": 4.369274139404297, "identity": 0.23533207178115845, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/673ea7a0e38872c7a4583151f076f8b45e5df628cf41244bd3e3ba5871c9f039.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "6752859cb25d2cb76247c4949fe1ed5d5b60a589162898bbb737af59b1e0e124", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a54a673c1b801b525b2c92bc490869a18b93afc4ce190b86c0ad191e4f0aa5d2", "generation_seconds_batch": 22.854820701060817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.042339056730270386, "target_z": -0.18066405404142818, "ce": 6.292664527893066, "genuineness": 4.419482707977295, "identity": 0.5589705109596252, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/6752859cb25d2cb76247c4949fe1ed5d5b60a589162898bbb737af59b1e0e124.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "67546cc2081227ae39b7b8f0b60821897499174cde946cc3d2a6b6e98023c9e7", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "845a46582287552bc81117cc380b38050d6ba89e3a638b003ba9b444ac3f8864", "generation_seconds_batch": 23.813998348079622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30592602491378784, "target_z": 0.4472656003176101, "ce": 6.395919322967529, "genuineness": 4.6956281661987305, "identity": 0.7818726301193237, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/67546cc2081227ae39b7b8f0b60821897499174cde946cc3d2a6b6e98023c9e7.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "680123ac50469827e25b2d5bebef42ef6bd32dc97151ca4b0ac9869fb3314e8f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a7af451ac1b5e23d330dccc05887de16b2e953ab1fd9a3c27654b782a33d2154", "generation_seconds_batch": 23.886877520009875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4100490212440491, "target_z": 0.6953124500805598, "ce": 6.221180438995361, "genuineness": 4.111956596374512, "identity": 0.2183009386062622, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/680123ac50469827e25b2d5bebef42ef6bd32dc97151ca4b0ac9869fb3314e8f.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": "685a12a0a237e12f5833945ef365d2b0cffd6b6e8a7d59c3fa42c24317fe8f0c", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "16d4f91af34c774436901790dc5cbfb3fde2189beefb3cc63a6ced9faa6395a9", "generation_seconds_batch": 16.732073032064363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0692214965820312, "target_z": 2.2656250776524627, "ce": 6.356205940246582, "genuineness": 4.7081804275512695, "identity": 0.538155198097229, "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_Awe/685a12a0a237e12f5833945ef365d2b0cffd6b6e8a7d59c3fa42c24317fe8f0c.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": "685b246fd4f99ae32e88d11a70de1887296cd4aab8337fd8c87efaca32de0724", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eed7e6413c490accd465b6b64f06496b47e24ff3e38cb6ef23bd85d7fce2b851", "generation_seconds_batch": 17.110133982030675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16695871949195862, "target_z": 0.1162109481772136, "ce": 6.332377910614014, "genuineness": 4.6203155517578125, "identity": 0.5816603302955627, "hypothesis": "Die Schlüss 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_Awe/685b246fd4f99ae32e88d11a70de1887296cd4aab8337fd8c87efaca32de0724.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "68f616e97f360ffd747a925107f4d475d4487f3a97a8b97ef9a0987c198ed704", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "333652d2a4332dc5ca30a31fad49d541dd4d44f03985a8aa86e939cffa32cc73", "generation_seconds_batch": 24.565155444084667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6822446584701538, "target_z": 1.3437500931829551, "ce": 6.157639026641846, "genuineness": 4.482243061065674, "identity": 0.7099602222442627, "hypothesis": "J'ai trouvé la 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_Awe/68f616e97f360ffd747a925107f4d475d4487f3a97a8b97ef9a0987c198ed704.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "68f7aaeaa18febd6e4f7b1b33968de4a380c952d09855d07f8328ad598f9d59b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "32d64f11fc93533d1829db437d3aebdc549ac71639308ed0c98fa32770355a12", "generation_seconds_batch": 24.291074660024606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2987840175628662, "target_z": 2.8125000443728356, "ce": 5.788304805755615, "genuineness": 4.457139015197754, "identity": 0.4787178933620453, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/68f7aaeaa18febd6e4f7b1b33968de4a380c952d09855d07f8328ad598f9d59b.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "692426dcf2bba872c8310c33dffa3661e168e585c6045d3a6ad2e08e4db1af5f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "840ba3a80074f2e8075c6e39c56d4b1c468e0e90eee2d3a4d856540a51798bc2", "generation_seconds_batch": 27.968990375986323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8890876770019531, "target_z": 4.218750039935552, "ce": 6.133810997009277, "genuineness": 4.425758361816406, "identity": 0.45410293340682983, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/692426dcf2bba872c8310c33dffa3661e168e585c6045d3a6ad2e08e4db1af5f.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "692b74cc69cd7de213ef486e3f4505f923b79c14c34b279290e2465fad4aa8d2", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "326bb3fb4da05c197d9d0a1e7618801858ff9cff8e9d07467f129b79ef8f70da", "generation_seconds_batch": 19.21654908300843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8691741228103638, "target_z": 1.7890625255143806, "ce": 6.197352409362793, "genuineness": 4.557555198669434, "identity": 0.2592655420303345, "hypothesis": "The 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_Awe/692b74cc69cd7de213ef486e3f4505f923b79c14c34b279290e2465fad4aa8d2.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": "69553e549d516983f3f852c87d1c80fb5006027a7eb6e27bbb50b2d90e55e588", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1fc10a11d9da4721b81451aaabcd57c82076c53f81371d93b3fbb5fceb35bbb8", "generation_seconds_batch": 23.529091028962284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7281571626663208, "target_z": 1.4531250865270298, "ce": 5.967014789581299, "genuineness": 4.532451152801514, "identity": 0.5399695634841919, "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_Awe/69553e549d516983f3f852c87d1c80fb5006027a7eb6e27bbb50b2d90e55e588.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "698120c1b189fff8377383f06c414afbce0c019ae015488e3c45f04868c0c047", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "69d7d5da2005d23f81282c504622b6b17052669e435cc4ca70126cdd2e1a6a6e", "generation_seconds_batch": 23.32593015593011, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5100727081298828, "target_z": 0.9335937261496008, "ce": 6.1894097328186035, "genuineness": 4.432034492492676, "identity": 0.25498008728027344, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/698120c1b189fff8377383f06c414afbce0c019ae015488e3c45f04868c0c047.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "69a0cc92abd3e058606ad2f3e4cb25c07fd113922412ae71da7fabe60f6eb268", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5cc94f077da03c8f8fba6266bc96b46ef373ed0901d02d98465d437e0f480351", "generation_seconds_batch": 22.805094340001233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08005289733409882, "target_z": -0.09082031457997668, "ce": 6.229123115539551, "genuineness": 3.9676074981689453, "identity": 0.6932435631752014, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/69a0cc92abd3e058606ad2f3e4cb25c07fd113922412ae71da7fabe60f6eb268.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": "69aab6b775d440ce81c5178edf47183a4604c3bed6d94bf422bf51c3f2d99a2e", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Escribí el número en el sobre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "608368c1e13b9ec703a1d1bfbce833b95b40e16fe39f39ade227ebad01a4c45c", "generation_seconds_batch": 17.504039866034873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1544876098632812, "target_z": 2.468750146430358, "ce": 6.157639026641846, "genuineness": 4.381826400756836, "identity": 0.39652034640312195, "hypothesis": "Escribí el número en el sobre. Léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/69aab6b775d440ce81c5178edf47183a4604c3bed6d94bf422bf51c3f2d99a2e.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": "69e15796ca79c0b29969e37098ba047b20522d856882d3730814fda8e0b8450b", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The keys are on the kitchen table.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "68dd8f93b1d161f36759c2f8695f6ae2893b3cb2c11e5b661e91378600285f6b", "generation_seconds_batch": 23.051724942051806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4037269353866577, "target_z": 3.0625001508676415, "ce": 6.252951145172119, "genuineness": 4.469690799713135, "identity": 0.6123257279396057, "hypothesis": "The keys are on the kitchen table. I checked the drawer that looked beside the window. Take them with you when you leave,", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/69e15796ca79c0b29969e37098ba047b20522d856882d3730814fda8e0b8450b.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "ec6d2f141b06e848ab15078d4b9fb015735390f2c89f1fb2430a54be11256e8e", "generation_seconds_batch": 20.280573131050915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09931975603103638, "target_z": -0.044921869730725754, "ce": 6.3641486167907715, "genuineness": 3.7793264389038086, "identity": 0.24831882119178772, "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_Awe/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "6a7769d8e72ef8af3cb5145fd01fa48535c73711e2e187308ce366e4e77c718c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3f0c1858279d588497a6633ed4bcd51d81c168a143b6a1c8ca5fb3c863a408cc", "generation_seconds_batch": 23.99432227399666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9284412860870361, "target_z": 4.312500115369373, "ce": 6.197352409362793, "genuineness": 4.532451152801514, "identity": 0.5298340916633606, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/6a7769d8e72ef8af3cb5145fd01fa48535c73711e2e187308ce366e4e77c718c.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "6a8c0f430593c95769bfa8a9f6cbf2a7e31f2867ae0011aab02d4e4e40289ccc", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5a7c4042b6034e8aa793fee275fa6497224d3bce5e5e56c67b9f8797de6de54d", "generation_seconds_batch": 17.234794431948103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1216928958892822, "target_z": 2.390624988906791, "ce": 6.316492557525635, "genuineness": 4.482243061065674, "identity": 0.41775333881378174, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/6a8c0f430593c95769bfa8a9f6cbf2a7e31f2867ae0011aab02d4e4e40289ccc.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": "6ab59fd6437506818955dd5daa5cfc88e0f29414c3dabd1f347b28111a58eeb3", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f06ba5247877a7a638213a94a779d1b832fc77c6cf3cb115c3cacb9dbd1250a7", "generation_seconds_batch": 17.28300430206582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5773017406463623, "target_z": 1.0937499866881493, "ce": 5.7684478759765625, "genuineness": 4.557555198669434, "identity": 0.8307361602783203, "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_Awe/6ab59fd6437506818955dd5daa5cfc88e0f29414c3dabd1f347b28111a58eeb3.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": "6ae04cc7b5469f2d0eda7d8681da0469dce1a1dfca1245bb9b6f880c60d8554c", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "26d350f53e40eee2c5d9c8abe0d135edee01a9a88562862cc93c9a55d895f66c", "generation_seconds_batch": 23.808462685905397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1151340007781982, "target_z": 2.375000070996537, "ce": 6.300607204437256, "genuineness": 4.337893962860107, "identity": 0.2971705496311188, "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_Awe/6ae04cc7b5469f2d0eda7d8681da0469dce1a1dfca1245bb9b6f880c60d8554c.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "6b7f9f3bb64c88f5002e55f33048e4fbfbe99f9b74a80776d39ee9eacbd7e551", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "16dd9c5580b1d511ff7baebe5c5ee5d9e5aa32155d10aed57f817db9e29506fd", "generation_seconds_batch": 24.474330081953667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8298205733299255, "target_z": 1.6953125920736343, "ce": 6.292664527893066, "genuineness": 4.356721878051758, "identity": 0.38467615842819214, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/6b7f9f3bb64c88f5002e55f33048e4fbfbe99f9b74a80776d39ee9eacbd7e551.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "6d3013d5c12cad560d61023ad1ff05e85ce3b7334dc0a25acc5906a7c4b927b2", "generation_seconds_batch": 20.360484486911446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09931975603103638, "target_z": -0.044921869730725754, "ce": 6.268836498260498, "genuineness": 4.557555198669434, "identity": 0.6998239755630493, "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_Awe/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.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": "6bbc0ab979d994e9a46e67cdf98fba09986280dfa2a1c7e4d9be58dde83e1e8c", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6bf691b7c532f717b3004543e47fa00ccff430eac006f50798f0247e8addc2db", "generation_seconds_batch": 18.74349991697818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.859335720539093, "target_z": 1.7656250066559254, "ce": 6.332377910614014, "genuineness": 4.331617832183838, "identity": 0.23987244069576263, "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_Awe/6bbc0ab979d994e9a46e67cdf98fba09986280dfa2a1c7e4d9be58dde83e1e8c.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "6bcfe43eaa9f41652fcae57d594e1319505e16c835192e7ed18aac18969ec391", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5299034f7770e27fddbbc97610151a0359999a58181f300bbe92bd029d5d2c68", "generation_seconds_batch": 29.514304826036096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.164562702178955, "target_z": 4.875, "ce": 6.300607204437256, "genuineness": 4.557555198669434, "identity": 0.4775378406047821, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/6bcfe43eaa9f41652fcae57d594e1319505e16c835192e7ed18aac18969ec391.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": "6bf2746511634bca864ee4b2a609ab7621fafd17b4418162a586b9813eda6ecc", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "b35f86b3b1c8f0161a2183362b034edd7aa122607df9bcfc5d2eeca01ad0b515", "generation_seconds_batch": 17.249531714012846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2266358137130737, "target_z": 2.640625095401597, "ce": 6.0146708488464355, "genuineness": 4.65797233581543, "identity": 0.5880309343338013, "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": 0.120000000000001, "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_Awe/6bf2746511634bca864ee4b2a609ab7621fafd17b4418162a586b9813eda6ecc.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "6bfa635b7e8b2eaf22266573a9b5d0e3bed841a33abf3bd7bc51db835cf0a559", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9271cfbe8344866846f4b877d1084ec294c8a2e2d4fda7e6f4492a3492abcd4b", "generation_seconds_batch": 23.74398925807327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4887561798095703, "target_z": 0.8828124589551269, "ce": 6.1894097328186035, "genuineness": 4.482243061065674, "identity": 0.7086526155471802, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/6bfa635b7e8b2eaf22266573a9b5d0e3bed841a33abf3bd7bc51db835cf0a559.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "6c287d84ca4da16442e16df2438f4c15147bf20a6f28f76e464fcf6704c2a409", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "650f913275305643a55d1f2d0aace6ccf2ab76ad5e4d52ec897c9505a77e9136", "generation_seconds_batch": 23.865435277926736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9153233766555786, "target_z": 4.281249995562717, "ce": 6.348263263702393, "genuineness": 4.632867813110352, "identity": 0.23930597305297852, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/6c287d84ca4da16442e16df2438f4c15147bf20a6f28f76e464fcf6704c2a409.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": "6ceb396b272bdabd1a9aeda3c9ef6f207eda5d45633da652860b7f6b77128749", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "17e125a7bc70d8912c79a1f9011b663e5825b82732be94d402327cfb8d59d7b5", "generation_seconds_batch": 24.040325321024284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17392757534980774, "target_z": 0.13281249445339552, "ce": 6.086154937744141, "genuineness": 4.331617832183838, "identity": 0.1942698359489441, "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_Awe/6ceb396b272bdabd1a9aeda3c9ef6f207eda5d45633da652860b7f6b77128749.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "6d3dc43be6a2c55a7f07685f25dcf6324deb9916c0528729935e907b8197863f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2ac1f105a1154e71226524976ecb88333ab266a8cc470eda15ee452a2cb68e58", "generation_seconds_batch": 24.565155444084667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0167499780654907, "target_z": 2.140624882411985, "ce": 6.09409761428833, "genuineness": 4.375550270080566, "identity": 0.597923994064331, "hypothesis": "J'ai trouvé la 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_Awe/6d3dc43be6a2c55a7f07685f25dcf6324deb9916c0528729935e907b8197863f.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "6df71b78909b8796ff7b9859d1bd3cbb1e8fa98ede257ce91ff7af06caeb14e1", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a819bdcd6994c2f40a1b6fc71da6c61b779a7aee87b9c7343ac0e7e626ea3579", "generation_seconds_batch": 17.36622269405052, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3250197172164917, "target_z": 2.875, "ce": 5.903473377227783, "genuineness": 4.250029563903809, "identity": 0.36314821243286133, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/6df71b78909b8796ff7b9859d1bd3cbb1e8fa98ede257ce91ff7af06caeb14e1.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "6df8eadf65e211d56b5cfa00ca66421c8fe66a71eafac6bc3b187e3f61797ead", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "43e27c44cd3dbc9d1b92ac0ca987edbd3dbfec93c9f2e10caa6da82da07994b8", "generation_seconds_batch": 23.999984991038218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.813423216342926, "target_z": 1.6562500133118507, "ce": 6.316492557525635, "genuineness": 4.469690799713135, "identity": 0.5229581594467163, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/6df8eadf65e211d56b5cfa00ca66421c8fe66a71eafac6bc3b187e3f61797ead.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "6e4babfa2156d80ca7cb62b2f468e5100733fbf638e9099bb8f9e878caa995b0", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3e0674b3443bbda9fae48f734457c628cdbc0803584b639c1c749aab66fb187d", "generation_seconds_batch": 24.042862550006248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5969785451889038, "target_z": 1.1406250244050598, "ce": 6.213237762451172, "genuineness": 4.080576419830322, "identity": 0.26293495297431946, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/6e4babfa2156d80ca7cb62b2f468e5100733fbf638e9099bb8f9e878caa995b0.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "6ec13ba5de167ee8c2f2db68d46058662a95a57cf9147505ba8633ad30ed2f01", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ad7a1bb7f4244f5702e0eeafedac79305047288502e895719d6af16af961d9ac", "generation_seconds_batch": 24.03958803298883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6953625082969666, "target_z": 1.3750000709965373, "ce": 5.935244083404541, "genuineness": 4.6203155517578125, "identity": 0.27645784616470337, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/6ec13ba5de167ee8c2f2db68d46058662a95a57cf9147505ba8633ad30ed2f01.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "6f4169a4376d739857dd8cef12744a18d78b5b177365355c9a83c46b906db01e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "0527661a8f0d4846d4a2ef915f6502548bc02bd5a7e024e305b9ec0b160ee8d1", "generation_seconds_batch": 28.647992874030024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4100490212440491, "target_z": 0.6953124500805598, "ce": 5.9431867599487305, "genuineness": 4.645420074462891, "identity": 0.7670115232467651, "hypothesis": "La porte est encore ouverte j'ai posé ton manteau sur la chaise dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/6f4169a4376d739857dd8cef12744a18d78b5b177365355c9a83c46b906db01e.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "6f4d24e53169361cbc7975e51656f1c8818eafc9a323a4f3b0073cf1fc236ec0", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "280d6e141c6b46c338aebbfbdb0a6bd11dd5a82f9f030f23429adb0f7f339271", "generation_seconds_batch": 23.227530956966802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09563035517930984, "target_z": -0.053710939302646456, "ce": 6.157639026641846, "genuineness": 4.444586753845215, "identity": 0.7628732323646545, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/6f4d24e53169361cbc7975e51656f1c8818eafc9a323a4f3b0073cf1fc236ec0.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "6f727f9171144c4481d4a87b4b379fc72feff7a347e201185c634560ce5ca7fd", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5597cfdda3192b08dc1e359c4192ebb03ebe815e63512d55bca5e2cb0108f415", "generation_seconds_batch": 24.009547177003697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8462178707122803, "target_z": 1.7343750288423432, "ce": 6.141753673553467, "genuineness": 4.7458367347717285, "identity": 0.7660884857177734, "hypothesis": "J'ai trouvé la 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_Awe/6f727f9171144c4481d4a87b4b379fc72feff7a347e201185c634560ce5ca7fd.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "6ff94f62464f35b7f139bd8e4f785ae23a99eb6c15ba527e3ed21be8ec76e2ff", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "66a06a0aa5ea27a18be44c70e669ef1891ff844fb0442ee79428ee564cb06e6f", "generation_seconds_batch": 16.933239127974957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11202768236398697, "target_z": -0.014648431537400195, "ce": 6.1894097328186035, "genuineness": 4.557555198669434, "identity": 0.30969905853271484, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/6ff94f62464f35b7f139bd8e4f785ae23a99eb6c15ba527e3ed21be8ec76e2ff.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "703f1b15fa8b9efe67ba174dcc4d0434e38c0a8ca03302cd445d5dd1d2901458", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c0dd60adbcaee903c7e0f525d968cf07cc1c1cb7eff2846e1d8c1d7c49e0ac97", "generation_seconds_batch": 17.288380017038435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09808995574712753, "target_z": -0.04785155958803265, "ce": 6.300607204437256, "genuineness": 4.545003414154053, "identity": 0.3865612745285034, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/703f1b15fa8b9efe67ba174dcc4d0434e38c0a8ca03302cd445d5dd1d2901458.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "708a8b22e4bc08a4702f41bb5704288fb87280c04230b563bcd32ee487a48163", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "226fc9a3d59d44d50b4f22f4ba6e80b25c42517188dd37092bd89d07fa32cbc9", "generation_seconds_batch": 24.388069521053694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04151918739080429, "target_z": -0.18261718652934422, "ce": 6.300607204437256, "genuineness": 4.419482707977295, "identity": 0.7116656303405762, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/708a8b22e4bc08a4702f41bb5704288fb87280c04230b563bcd32ee487a48163.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "71d3f410a841f3b2f85a97d96aef8b15202e54cc534ff82deb54d61973a3d0e6", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "7b8833da32b318625bae2857f32bc934902686abdf89ade09d0eb609d0d80db6", "generation_seconds_batch": 24.605119501939043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30264657735824585, "target_z": 0.4394531413624832, "ce": 6.340320587158203, "genuineness": 4.6956281661987305, "identity": 0.3860464096069336, "hypothesis": "Die Tür 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_Awe/71d3f410a841f3b2f85a97d96aef8b15202e54cc534ff82deb54d61973a3d0e6.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": "71e50c24b6669c11d6c43cbde2324dd6e2365628cbce45db811774883afde261", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3ea8effba82e4ff37051f0c751e58aba652117774f0e4fc98b96fd272cf77227", "generation_seconds_batch": 18.228595850989223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9118071794509888, "target_z": 1.8906250599033283, "ce": 5.95112943649292, "genuineness": 4.720732688903809, "identity": 0.7730369567871094, "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_Awe/71e50c24b6669c11d6c43cbde2324dd6e2365628cbce45db811774883afde261.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "72589236f97e70fcf88a610a9bb76ed9fabeedbf235907c803672f91efe14ee5", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a50a8ec35f77ad3441342a5b5f8baf20298534b77924c2536adea12db9c2377c", "generation_seconds_batch": 26.400119371013716, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4494026005268097, "target_z": 0.7890624545178433, "ce": 6.09409761428833, "genuineness": 4.344170093536377, "identity": 0.39413121342658997, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/72589236f97e70fcf88a610a9bb76ed9fabeedbf235907c803672f91efe14ee5.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "726727979298213dacc0114bbc6eafad2e8cd52564ad5b1460e00584c74c071c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "dd674abf1e3246cba31623f9169ade4f48737b9ba235ea8152963c6668397925", "generation_seconds_batch": 22.819348535966128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1085749864578247, "target_z": 2.3593748691001344, "ce": 6.2767791748046875, "genuineness": 4.758388519287109, "identity": 0.6362269520759583, "hypothesis": "J'ai trouvé la 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_Awe/726727979298213dacc0114bbc6eafad2e8cd52564ad5b1460e00584c74c071c.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": "72bff9005b34d1a877df59bb3ade3500a3280fe2083be516019c516e790a4df7", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Escribí el número en el sobre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fe97548bc553ccbfe554591f1ede1122d84943ca0f24827262e431d9f892053b", "generation_seconds_batch": 23.364312798017636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.852776825428009, "target_z": 1.7500000887456715, "ce": 6.062326908111572, "genuineness": 4.632867813110352, "identity": 0.5367835760116577, "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_Awe/72bff9005b34d1a877df59bb3ade3500a3280fe2083be516019c516e790a4df7.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "7381815d5033309d26132109b2a437f7c042c37b6cfe19295250446191f404e2", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f5484dbb05a1f9c915b1ce301df0b2ee179bcc605f91f3876de9199b534bf850", "generation_seconds_batch": 23.06170879898127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4903959333896637, "target_z": 0.8867187594292276, "ce": 6.372091293334961, "genuineness": 4.557555198669434, "identity": 0.6173738837242126, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/7381815d5033309d26132109b2a437f7c042c37b6cfe19295250446191f404e2.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "7486235d3c050773a8c6a98e6e12f1384a110afe422d895698d7110642806603", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "372dc091eb8fb24c806bf32961b9575439a9017ee687d4f41e83eb538cc209c8", "generation_seconds_batch": 17.449256908963434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.112091302871704, "target_z": 4.750000088745671, "ce": 6.38003396987915, "genuineness": 4.632867813110352, "identity": 0.40098151564598083, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/7486235d3c050773a8c6a98e6e12f1384a110afe422d895698d7110642806603.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": "74c2eabb313d251cb72ef9e0ee293b00bd922bce7dd5e25b272ee7e0ce438844", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7ff745c5fd584d2f44072bd8aa7bcfd94ce7051f1ace00d76010feb87181cc82", "generation_seconds_batch": 17.34593644097913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2723115086555481, "target_z": 0.36718747004833585, "ce": 6.260893821716309, "genuineness": 4.68307638168335, "identity": 0.6153512597084045, "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_Awe/74c2eabb313d251cb72ef9e0ee293b00bd922bce7dd5e25b272ee7e0ce438844.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "7514e033fca005fb78733825425ed796cc78423d32f6d7317ca413a4612f0a41", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "254c7a9a2aa6585edaed42148ff46a3ee953cd49910db8b4e2e8303746a7ee3e", "generation_seconds_batch": 23.813998348079622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.206722229719162, "target_z": 0.21093750998388805, "ce": 6.221180438995361, "genuineness": 4.595211505889893, "identity": 0.7105700969696045, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/7514e033fca005fb78733825425ed796cc78423d32f6d7317ca413a4612f0a41.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "7538862febcc677c08ef9742f39132683bf43c8350c97d3b332b5b5a330123ff", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "55764c6ba68905f71d6541f72275683f519ece268e9c346dcef194db950ee27f", "generation_seconds_batch": 23.89384314895142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6330526471138, "target_z": 1.2265624988906791, "ce": 6.23706579208374, "genuineness": 4.557555198669434, "identity": 0.7174872159957886, "hypothesis": "J'ai trouvé la 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_Awe/7538862febcc677c08ef9742f39132683bf43c8350c97d3b332b5b5a330123ff.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "757cb8e2e1fa572a2cfb0f9c5e8e41086f72ef4a9811adedf714d89610df85fa", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6162a11954a370c5d5e8b71d0a707b46750f127d8ca6c3dd1516110201c92028", "generation_seconds_batch": 17.77762654691469, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23623740673065186, "target_z": 0.2812499955627164, "ce": 5.9431867599487305, "genuineness": 4.582659721374512, "identity": 0.7381786108016968, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/757cb8e2e1fa572a2cfb0f9c5e8e41086f72ef4a9811adedf714d89610df85fa.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "75b7f85a0ab51cc731f1f474848722a879c6dc43dfae068d9f13960d17ed7318", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "74069d504e03f47364a830bf77b5da240a661e9b12b149960feca168b8ddda97", "generation_seconds_batch": 25.90254520298913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5149919390678406, "target_z": 0.9453125565753656, "ce": 5.95112943649292, "genuineness": 4.030367851257324, "identity": 0.5152761936187744, "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_Awe/75b7f85a0ab51cc731f1f474848722a879c6dc43dfae068d9f13960d17ed7318.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "75bc31a60a68382c42419e16e0fa6fad0e7d33649f619d296685fc568478616d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ff741de55db3febb5be58cf9b5643cce4887a844e021227b69236d23bac1da17", "generation_seconds_batch": 22.540899846004322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.162449449300766, "target_z": 0.10546874611737687, "ce": 6.197352409362793, "genuineness": 4.369274139404297, "identity": 0.6429898142814636, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/75bc31a60a68382c42419e16e0fa6fad0e7d33649f619d296685fc568478616d.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": "75e8922e67c061be802cdcdf06401ce654e3f6e7bca5b1f710ce3f30b2aa34c9", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "6c9a19435826a7dab896ec84e8d022dfd066c7b66794ab08e0be4eea1b4954e2", "generation_seconds_batch": 24.739027956034988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9773964881896973, "target_z": 2.0468750909643134, "ce": 5.792276382446289, "genuineness": 4.532451152801514, "identity": 0.8445671796798706, "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": 0.120000000000001, "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_Awe/75e8922e67c061be802cdcdf06401ce654e3f6e7bca5b1f710ce3f30b2aa34c9.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "761ac35314186cfb290f9a1421f4537f4f69492aa7bd725c52d6074ad66ea884", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7b67b65e6510127bbe1e4e6fdd3f959640cb689750581f1c13d0cdcff4188d6e", "generation_seconds_batch": 22.39641169901006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6133758425712585, "target_z": 1.1796874611737687, "ce": 5.863759994506836, "genuineness": 4.162164688110352, "identity": 0.4850034713745117, "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_Awe/761ac35314186cfb290f9a1421f4537f4f69492aa7bd725c52d6074ad66ea884.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "76a7a2d4b4458f490783417cc508a98c5db53a71495bdbd344bcf00c28208bf8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "b8d099266129699510cf4180423b3a849776a5ed7499ddaa3b819e6527da2b29", "generation_seconds_batch": 17.391618467052467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8396589756011963, "target_z": 1.7187501109320893, "ce": 6.435632705688477, "genuineness": 4.7458367347717285, "identity": 0.6695761680603027, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/76a7a2d4b4458f490783417cc508a98c5db53a71495bdbd344bcf00c28208bf8.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": "76b3c18011a17283c7f7a02f05315e811cc530c2cfe6e28f989ab4f7f51a9a10", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4dc32fc4c5f060de6d9463e9dac2d59110580ccd26aef1bf26a430d06961bd41", "generation_seconds_batch": 21.939212242956273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5773017406463623, "target_z": 1.0937499866881493, "ce": 6.41180419921875, "genuineness": 4.6956281661987305, "identity": 0.5719243884086609, "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_Awe/76b3c18011a17283c7f7a02f05315e811cc530c2cfe6e28f989ab4f7f51a9a10.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "76f4d31e23a056825810948a90ae7fdd7420d936844d4170aa240d1e43c555aa", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "33518ea532f9c6b63c47903495a67d45152d441780d5cda4bd04ab2d4f51a657", "generation_seconds_batch": 22.725501523935236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11243761330842972, "target_z": -0.01367187416800933, "ce": 6.229123115539551, "genuineness": 4.645420074462891, "identity": 0.2782641053199768, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/76f4d31e23a056825810948a90ae7fdd7420d936844d4170aa240d1e43c555aa.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "7747c3ec02129c1ee3f2e417630d493991f3711a28740d95340f3bb249e98169", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1bdeb7ae73482e56b73d50c9542b75c092b9b9d666745ac88abd9a38422c5d64", "generation_seconds_batch": 22.230071795987897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8366162776947021, "target_z": 4.093750128681224, "ce": 6.395919322967529, "genuineness": 4.557555198669434, "identity": 0.3240365982055664, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/7747c3ec02129c1ee3f2e417630d493991f3711a28740d95340f3bb249e98169.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "775971dca63f1475657e5661c55f118af53941fe3e535a85e70704c3be641b84", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "84db1d175311c32a26a53ccfe9613705518e1a440b1535ed2966714386e56d6a", "generation_seconds_batch": 16.37060394603759, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.400684118270874, "target_z": 5.437499884630627, "ce": 6.157639026641846, "genuineness": 4.507347106933594, "identity": 0.49149513244628906, "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_Awe/775971dca63f1475657e5661c55f118af53941fe3e535a85e70704c3be641b84.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "55febec594e26408327615bb2860ea48755f593da3c162cbfee4cd5ef45c5bc6", "generation_seconds_batch": 16.511451895930804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25755393505096436, "target_z": 0.3320312627571903, "ce": 6.09409761428833, "genuineness": 4.469690799713135, "identity": 0.7486202716827393, "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_Awe/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "77e6a49811aaa6f111db6f81a7346cd441499311bec367b94c9d70f620072d48", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d7e4f3eeca96e0dc90acfe1133439cadc1a3941a3443f00af589b4222a68dc0d", "generation_seconds_batch": 23.555408046930097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05709664523601532, "target_z": -0.145507811252014, "ce": 6.0305562019348145, "genuineness": 4.507347106933594, "identity": 0.5580354332923889, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/77e6a49811aaa6f111db6f81a7346cd441499311bec367b94c9d70f620072d48.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "77f1fae82b86dbe59b0476f9e312e3c92a9229cb9489e84551b0d663b96e24db", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "906000022e31b4942019cd11c10d3d50519be16e85c280772c1cb4d354dc8731", "generation_seconds_batch": 17.50173798506148, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30018696188926697, "target_z": 0.4335937261496008, "ce": 5.414999485015869, "genuineness": 4.419482707977295, "identity": 0.431898295879364, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/77f1fae82b86dbe59b0476f9e312e3c92a9229cb9489e84551b0d663b96e24db.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": "786db70cf99f6ccc6e315b0d028e502236b5e54cba0a2c7bd9a31476a57d3733", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4c9e7f8793cb21454b3b6ac42631403491dbdc52d43c0bac89ea8668c9bc1c54", "generation_seconds_batch": 17.1468774729874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2922251224517822, "target_z": 2.7968751264625817, "ce": 6.117925643920898, "genuineness": 4.457139015197754, "identity": 0.5889099836349487, "hypothesis": "Die Schlüsse liegen auf dem Küchentisch. Ich suchte in der Schublade, daneben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.14285714285714285, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/786db70cf99f6ccc6e315b0d028e502236b5e54cba0a2c7bd9a31476a57d3733.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "78e3d5f7a28da4751bf3e2bb5e3381de9d5c6a8a9ce393a920c249d9a165d13c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a128d4b92f130b9d9bf803e2a4073a3c7e7f5d0a8605fce3d0146fe9d0b4051c", "generation_seconds_batch": 23.449394820956513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7185555696487427, "target_z": 3.8125001863659103, "ce": 6.3641486167907715, "genuineness": 4.582659721374512, "identity": 0.5334814190864563, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/78e3d5f7a28da4751bf3e2bb5e3381de9d5c6a8a9ce393a920c249d9a165d13c.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "3f949af5fe2525667a493c2223687357d3247fd2e3e9edf40e64c97fbb3ada38", "generation_seconds_batch": 17.929084462928586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.195654034614563, "target_z": 0.18457031901726026, "ce": 6.395919322967529, "genuineness": 4.6705241203308105, "identity": 0.7282077074050903, "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_Awe/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "796cc53acde269616d4c5cfe917e038df07f23c229f97e2afe09f5a09c996bb8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1b0b44c223c4ee930d37e047c0ed771b52b9ef110afcfe3d07f6a42edd895d8d", "generation_seconds_batch": 21.12012975604739, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23131820559501648, "target_z": 0.26953123613348884, "ce": 6.205295085906982, "genuineness": 4.18099308013916, "identity": 0.2495255023241043, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/796cc53acde269616d4c5cfe917e038df07f23c229f97e2afe09f5a09c996bb8.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": "7a6f21d82ba25445c7abf08c5cb6916ce5107f70aee98acf1d2fd2a5fc9273cc", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af34826300e87cc832684685c9ee39f48075bef400643d2add0f9a934f7b6fac", "generation_seconds_batch": 23.316752639017068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6002579927444458, "target_z": 1.1484374833601867, "ce": 6.316492557525635, "genuineness": 4.319066047668457, "identity": 0.5715012550354004, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het naar de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/7a6f21d82ba25445c7abf08c5cb6916ce5107f70aee98acf1d2fd2a5fc9273cc.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": "7afc1c1895a8f1eba08a9b7bab83de00e1d806acc75f1070b929a15a4179541f", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2854a101411c39bffcf983f60fda51420a6ca93718303971a700fa84c8dadc12", "generation_seconds_batch": 16.444532596040517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1544876098632812, "target_z": 2.468750146430358, "ce": 6.332377910614014, "genuineness": 4.519899368286133, "identity": 0.5771517157554626, "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_Awe/7afc1c1895a8f1eba08a9b7bab83de00e1d806acc75f1070b929a15a4179541f.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "7b20a65b30deb49d9a8c0f1956c3ab649f58fb2a847b3cf5e28424165d566703", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "50baa9f190f4ca9aff0ac92ba215364186fc2a114691c1acc9a7a7b16d0f591e", "generation_seconds_batch": 23.74398925807327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09890982508659363, "target_z": -0.04589842710011662, "ce": 6.165581703186035, "genuineness": 4.362998008728027, "identity": 0.6796059608459473, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/7b20a65b30deb49d9a8c0f1956c3ab649f58fb2a847b3cf5e28424165d566703.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "7bc0dadb28377cc635ee2c2c49e036e8ff550d44a391ac79a36288b4a20c6a95", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f32f69a7e312d095a3a4c950151d3e8df76e77da4598067ec9b8eda6abc9c3cc", "generation_seconds_batch": 27.450073151965626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9577196836471558, "target_z": 2.000000053247403, "ce": 6.395919322967529, "genuineness": 4.193545341491699, "identity": 0.5445582866668701, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/7bc0dadb28377cc635ee2c2c49e036e8ff550d44a391ac79a36288b4a20c6a95.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "7bee74cc90cb7866308ee31f748de9fffa600592b0cbb7208a68d4ecfb392136", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d039608f9813e73ce44a9dabfaf033c0a12c5aa36ca6595bada44e51830563aa", "generation_seconds_batch": 24.59099932794925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09727008640766144, "target_z": -0.04980469207594869, "ce": 6.205295085906982, "genuineness": 4.381826400756836, "identity": 0.5834566950798035, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/7bee74cc90cb7866308ee31f748de9fffa600592b0cbb7208a68d4ecfb392136.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "7c2ebb6243a614acd95a66d027da01bbd00bd4042d5a48eb326daf0d95e9fe4f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5936605d64179f47236e0652745210c1757335f1dccdbdd8392d5f0fe19eecc8", "generation_seconds_batch": 24.495312712038867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.250995010137558, "target_z": 0.3164062738503992, "ce": 6.022613525390625, "genuineness": 4.607763767242432, "identity": 0.3018679618835449, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/7c2ebb6243a614acd95a66d027da01bbd00bd4042d5a48eb326daf0d95e9fe4f.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "7c3731da16568cae719e74e4877563eda92373b68ca0bd3d82ab137300013b48", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9150f5f7bf4a6dd3b17fbbc6ca7d639196a9fa4413fd7c96d6dcefcc14b7900a", "generation_seconds_batch": 17.50173798506148, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5609044432640076, "target_z": 1.0546875499194401, "ce": 6.046441555023193, "genuineness": 4.394378662109375, "identity": 0.6977977752685547, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/7c3731da16568cae719e74e4877563eda92373b68ca0bd3d82ab137300013b48.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "7c84d4af02bdf46178d5a662a612d5840a160573742fce21e9f2e9ca02d9a0e0", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "811b26855775b876614a4468d18ee9454f88551c4c438dfdeeb0e1ff941b1743", "generation_seconds_batch": 22.322407337022014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4477628767490387, "target_z": 0.7851562250402799, "ce": 5.982900142669678, "genuineness": 4.482243061065674, "identity": 0.6110174655914307, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/7c84d4af02bdf46178d5a662a612d5840a160573742fce21e9f2e9ca02d9a0e0.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "7cbe0e824f216b31341ba3e708a22ad505f62c01d882c8ff813e759c743ede76", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1a79c5924143382d7e116fb25a0f3f9fb46b312bc2ece288094f2dcf841161aa", "generation_seconds_batch": 28.293835307005793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.810143768787384, "target_z": 1.6484375543567238, "ce": 6.0305562019348145, "genuineness": 4.432034492492676, "identity": 0.352329283952713, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/7cbe0e824f216b31341ba3e708a22ad505f62c01d882c8ff813e759c743ede76.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "7d8be5601355740319baecbbd15d5138e3fc009b51120ad2e3658f2eac1542d0", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c0a76bd16e32c712b5fc0f45329df1efd3214352cf5d5310bd8225710bb57513", "generation_seconds_batch": 17.55622039292939, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10710848122835159, "target_z": -0.026367190966627794, "ce": 6.1894097328186035, "genuineness": 4.256305694580078, "identity": 0.4124932289123535, "hypothesis": "De deur 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_Awe/7d8be5601355740319baecbbd15d5138e3fc009b51120ad2e3658f2eac1542d0.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "7e03ef179e225e2c6d5c54dcc8f83b88dc224212117e82c8a43e405914d663fa", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "8b6e85f08104b3407f8abed1bf863d3d1d7d565aa2c141887acaa4381480f9f5", "generation_seconds_batch": 24.393286861944944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08456216752529144, "target_z": -0.08007811252013994, "ce": 6.38003396987915, "genuineness": 4.65797233581543, "identity": 0.6033315658569336, "hypothesis": "Die Tür 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_Awe/7e03ef179e225e2c6d5c54dcc8f83b88dc224212117e82c8a43e405914d663fa.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "7e465be499afda87c7b775935803281cdfd1b53457ced2270bc1d4e3047a2d12", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2aa525e2d32e06064ac9a62f03ac5aa5ac4e1eb93f9cdb3c7feb16784ba65788", "generation_seconds_batch": 23.83297951996792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35101866722106934, "target_z": 0.554687478922903, "ce": 6.205295085906982, "genuineness": 4.174716949462891, "identity": 0.18881875276565552, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/7e465be499afda87c7b775935803281cdfd1b53457ced2270bc1d4e3047a2d12.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": "7e46adab604c425a4a29dee6fd6a560f9bcbf9a70ab92f1945063fc385f8e98a", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Your message arrived after I had left.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b8fdb1e5d5a8c5bc945a4aca417f84b55b1d270dcac1b3de888424f8b07b0b81", "generation_seconds_batch": 16.92870921699796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2919883131980896, "target_z": 0.4140625077652463, "ce": 6.332377910614014, "genuineness": 4.287685871124268, "identity": 0.2955932021141052, "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_Awe/7e46adab604c425a4a29dee6fd6a560f9bcbf9a70ab92f1945063fc385f8e98a.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "7e7989f1fa4b6acf9cd132879b6df35c931d7b776e3dc42820d6cc1f155ba7b2", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "e4b316258d2ebabadb6230d0c417847a8d6d5dcb984cdd0a59d188c8f4f292cc", "generation_seconds_batch": 24.14861163997557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12022633850574493, "target_z": 0.00488280459608863, "ce": 6.3641486167907715, "genuineness": 4.632867813110352, "identity": 0.47149649262428284, "hypothesis": "Die Tür 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_Awe/7e7989f1fa4b6acf9cd132879b6df35c931d7b776e3dc42820d6cc1f155ba7b2.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "7ed26bd0a48f1b104a4f9b9cb7d58a3184e6d61da2f9d2c97047574a3f033974", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "fd2f8b2172910d60c4e581930ec32d1131b63cf29953fd7c90a34117af345b6b", "generation_seconds_batch": 23.75589238095563, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8003053665161133, "target_z": 1.6250000354982685, "ce": 5.967014789581299, "genuineness": 4.20609712600708, "identity": 0.40887871384620667, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/7ed26bd0a48f1b104a4f9b9cb7d58a3184e6d61da2f9d2c97047574a3f033974.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "7edbb2d34c0b92a0938df55ba7706072141391e550bc8ced1eeabff199f295df", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "09975bbeaa9771ee315b98916b440325660cba4a0f5211889177e546ec7afff8", "generation_seconds_batch": 24.291074660024606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1085749864578247, "target_z": 2.3593748691001344, "ce": 5.990842819213867, "genuineness": 4.557555198669434, "identity": 0.4662504196166992, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/7edbb2d34c0b92a0938df55ba7706072141391e550bc8ced1eeabff199f295df.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "7f6521e75b776f65c62d23d68b2cdd7edaa2321638efa6ec2648ccd3b58d5140", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4e37f6cf303026150ea3c3d05a12f209f05249180ce941f13b8ebcffe92c248f", "generation_seconds_batch": 17.554142318083905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36741599440574646, "target_z": 0.5937499866881493, "ce": 6.372091293334961, "genuineness": 4.68307638168335, "identity": 0.7384899854660034, "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_Awe/7f6521e75b776f65c62d23d68b2cdd7edaa2321638efa6ec2648ccd3b58d5140.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "d5034823983cefb73034ad8689710a03c5b9a7a9133daefce5175989a7c91e9e", "generation_seconds_batch": 17.006943335058168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18868517875671387, "target_z": 0.16796877274107833, "ce": 6.459460258483887, "genuineness": 4.3127899169921875, "identity": 0.2249208688735962, "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_Awe/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "7f9921204511d116efc80c77278aef430f023fa6eec3d4ee8552f188f0849357", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e6eee539eafee49b680445e48f34bc6c2e7c004798782160ecc9ab5492865c87", "generation_seconds_batch": 23.50782528903801, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43300530314445496, "target_z": 0.7500000177491343, "ce": 6.117925643920898, "genuineness": 4.432034492492676, "identity": 0.6978639364242554, "hypothesis": "La puerta sigue abierta. He dejado tu abrijo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/7f9921204511d116efc80c77278aef430f023fa6eec3d4ee8552f188f0849357.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": "80b647f4b6b5972c208b74f4220dc912c32dbd16bae059916021c9057a50798f", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3b87f82ff674dd3f4fc404565dbc02608d3fa84094ab360679c8b8f998a6e77d", "generation_seconds_batch": 16.444532596040517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6166553497314453, "target_z": 1.18750006212197, "ce": 6.229123115539551, "genuineness": 4.344170093536377, "identity": 0.16166901588439941, "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_Awe/80b647f4b6b5972c208b74f4220dc912c32dbd16bae059916021c9057a50798f.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "e149b4003765fa10072f018edcd0fbce2d29bd8901119a533c62557bd20731f1", "generation_seconds_batch": 17.81157343601808, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34118029475212097, "target_z": 0.531250031060985, "ce": 6.229123115539551, "genuineness": 4.532451152801514, "identity": 0.5926368236541748, "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_Awe/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "80ede8daa3dda875152fc22def69b5419f4841630c664e72d6e7f83bcb901fe9", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c1d4733f12a2bdeebe6cfe7f4cc104b62ce5704ec3a48162b711a2bd5cd73539", "generation_seconds_batch": 21.99769961705897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36905571818351746, "target_z": 0.5976562161657127, "ce": 6.205295085906982, "genuineness": 4.381826400756836, "identity": 0.4189452528953552, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/80ede8daa3dda875152fc22def69b5419f4841630c664e72d6e7f83bcb901fe9.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "811eaf28992408ab6d26b41eee34e21033835d18214866a323c2ac064661387e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c32cc0c758e9226aff77d0947fbe204be96d280df6910a3554d2392a40edada7", "generation_seconds_batch": 24.559872444951907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.764231264591217, "target_z": 1.5390625610126492, "ce": 5.919358730316162, "genuineness": 4.243753433227539, "identity": 0.3873944878578186, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/811eaf28992408ab6d26b41eee34e21033835d18214866a323c2ac064661387e.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "8155a452727d15d945a730388d1f4659a27b9eab4c481f8ffb5e9c4b5a54544f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d88a73c2dc64aca1f005e9b2e957a69fb2ede694da6739fdd831a3359afc7427", "generation_seconds_batch": 21.12012975604739, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.678965151309967, "target_z": 1.3359374922347538, "ce": 6.165581703186035, "genuineness": 4.256305694580078, "identity": 0.2885512709617615, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/8155a452727d15d945a730388d1f4659a27b9eab4c481f8ffb5e9c4b5a54544f.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "81857d4f13272c28b9ab35889f4a25495a4e7ac06973ab89c48e5741cc2a4ab6", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ecf3453caa30b8f156fa432ecd319659b8339b29cfe2caee2062c2a75885be6f", "generation_seconds_batch": 27.550500173005275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23869700729846954, "target_z": 0.2871093752773302, "ce": 6.086154937744141, "genuineness": 4.7081804275512695, "identity": 0.5895191431045532, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/81857d4f13272c28b9ab35889f4a25495a4e7ac06973ab89c48e5741cc2a4ab6.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": "818ffdf4a791e02be2074507c9fa832adc57e1e653ce2f6466d7d15e51ca4e81", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ccf25279546120ebf82c0d9c1a2b1c220adb168765826d719e2e51c4fab2b679", "generation_seconds_batch": 23.491155444993638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4758751392364502, "target_z": 3.2343750998388803, "ce": 5.998785495758057, "genuineness": 4.419482707977295, "identity": 0.6926864981651306, "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_Awe/818ffdf4a791e02be2074507c9fa832adc57e1e653ce2f6466d7d15e51ca4e81.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "81920fa64b30b3de3b6220f082a06779d2347274478d5e9c9de692a5846286dc", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "594f3c19baf914e520d33940630439a61b712ff4a9c060231694375d4ce397b7", "generation_seconds_batch": 17.474869732977822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7478339672088623, "target_z": 1.50000012424394, "ce": 6.078212261199951, "genuineness": 4.394378662109375, "identity": 0.5652961730957031, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/81920fa64b30b3de3b6220f082a06779d2347274478d5e9c9de692a5846286dc.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "81f3a4565f4349d9e455485a267289cdfa597f3910e553f8409fda8d1ab93331", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "9eac09ee8298bac06d13ef1703950a25bc83a9d9bade38b6c28669f47d82d097", "generation_seconds_batch": 23.60745233600028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6136126518249512, "target_z": 3.5625000798711044, "ce": 6.356205940246582, "genuineness": 4.758388519287109, "identity": 0.6141576766967773, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/81f3a4565f4349d9e455485a267289cdfa597f3910e553f8409fda8d1ab93331.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "821eca72dd1af793ebb60e9a738b8fcdc76055b99845946d122d4e288b4a0b2f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "68fbe705105ae5dfaac962ff304828259d3b91af40a6fcefa7daa6e73f9a6e00", "generation_seconds_batch": 23.507644859026186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1804865002632141, "target_z": 0.14843748336018658, "ce": 5.677107334136963, "genuineness": 4.2751336097717285, "identity": 0.40330439805984497, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/821eca72dd1af793ebb60e9a738b8fcdc76055b99845946d122d4e288b4a0b2f.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "8255628813b06a9ab90ab82a9d14a4a61a6c122a39fd9fb6b17e94010dbd62f2", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "8f5f0fa76cf7beccb7153b56f149466051be32d7ed04cf181ef6a824ef26ffeb", "generation_seconds_batch": 16.815395866986364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15957991778850555, "target_z": 0.09863280903337221, "ce": 6.340320587158203, "genuineness": 4.68307638168335, "identity": 0.5496493577957153, "hypothesis": "Die Tür 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_Awe/8255628813b06a9ab90ab82a9d14a4a61a6c122a39fd9fb6b17e94010dbd62f2.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "8315271cfadb1a08510878e9d27fe46b76db1374fc3cd4ddcb83918e88af4601", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "897a397c541108f6562067d574ecbc18f711c11857521c672b4831db68b6b4c5", "generation_seconds_batch": 17.449256908963434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8234983682632446, "target_z": 4.062500008874567, "ce": 6.395919322967529, "genuineness": 4.570107460021973, "identity": 0.35495245456695557, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/8315271cfadb1a08510878e9d27fe46b76db1374fc3cd4ddcb83918e88af4601.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "83e776751c326340ba72d39ba2a6a6a05309a37af2d63934ec6cf8b45258d534", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0aea77529b4ba59f2f537cf8311748b22ec5d9a9315e55914aab844d52078974", "generation_seconds_batch": 24.202525199041702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.895409882068634, "target_z": 1.8515626231346192, "ce": 6.205295085906982, "genuineness": 4.6203155517578125, "identity": 0.5957348346710205, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/83e776751c326340ba72d39ba2a6a6a05309a37af2d63934ec6cf8b45258d534.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "8417b55178630c919b435aab3aa8483e5968a262ce5ac7d9a9766abf3026234e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3a50a29db53a1ae919b51e868be3e23f37604f9fee0a0f88511ddd3a343e6754", "generation_seconds_batch": 24.195559829939157, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10013961791992188, "target_z": -0.042968754991944025, "ce": 6.292664527893066, "genuineness": 4.093128204345703, "identity": 0.5423136949539185, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/8417b55178630c919b435aab3aa8483e5968a262ce5ac7d9a9766abf3026234e.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "851055206122d2e1cf4f5572c390a677ee133ec8fd9548a2937671a343a8d18c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2345e2b49fcb23afad20df28992fad86aadff90223b4b073cd247ee3dcb634f0", "generation_seconds_batch": 17.890956277027726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.767510712146759, "target_z": 1.546875019967776, "ce": 6.157639026641846, "genuineness": 4.846253395080566, "identity": 0.8503100872039795, "hypothesis": "J'ai trouvé la 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_Awe/851055206122d2e1cf4f5572c390a677ee133ec8fd9548a2937671a343a8d18c.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "85ab03ba90f6ed7c16e21053821886be029f924ec3abe4df7b97d189af60f106", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "54a747984ed0b82b33256da9445e5a52df9515a5534c50877b478c076be8139d", "generation_seconds_batch": 19.067096341983415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9642786383628845, "target_z": 2.015625113150731, "ce": 5.998785495758057, "genuineness": 4.7458367347717285, "identity": 0.7163956165313721, "hypothesis": "J'ai trouvé la 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_Awe/85ab03ba90f6ed7c16e21053821886be029f924ec3abe4df7b97d189af60f106.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": "8651b6cd0e31e122fbecea7090a4ad223d85365a18857eeab1bd817698b8ffc1", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d7e027571bbe82f127849e9b1479f7834370db4a6fbf3c930ffeb768442a533e", "generation_seconds_batch": 17.80240192601923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4955519437789917, "target_z": 3.2812501375557908, "ce": 6.2767791748046875, "genuineness": 4.432034492492676, "identity": 0.6709065437316895, "hypothesis": "Más llaves están en la mesa de la cocina. Miren el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.13043478260869565, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/8651b6cd0e31e122fbecea7090a4ad223d85365a18857eeab1bd817698b8ffc1.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "870ed8d5fb775d3ebf5d7d8b16a6cffb4e6188885add6d28b1d78973d7a31b5d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1cf1992dd6c2ac0704ba7f5fc08627c320e18161970025413bebd9be7fa690ec", "generation_seconds_batch": 24.58926977100782, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.085855484008789, "target_z": 4.687499849132358, "ce": 6.284721851348877, "genuineness": 4.469690799713135, "identity": 0.523067831993103, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/870ed8d5fb775d3ebf5d7d8b16a6cffb4e6188885add6d28b1d78973d7a31b5d.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "87824c3f786c2ef9d093e0159806ac7a6d89e85e001ef037d89892ab72d4b39d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "547603ad07a7d2d1ba65a5a142a1fba15875054a1f1dc164bb6e62224e0eab2b", "generation_seconds_batch": 25.90254520298913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6822446584701538, "target_z": 1.3437500931829551, "ce": 6.252951145172119, "genuineness": 4.482243061065674, "identity": 0.3003941774368286, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/87824c3f786c2ef9d093e0159806ac7a6d89e85e001ef037d89892ab72d4b39d.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": "8801b44604a493e2246c1773989c9317c41d53e0e2784f288aac2be049e7b9a4", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ed54582f73b160a4e726bc9fd204cce267d08a045fa9c7d133139917f0aae826", "generation_seconds_batch": 16.732073032064363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2069590091705322, "target_z": 2.5937500576846864, "ce": 6.197352409362793, "genuineness": 4.582659721374512, "identity": 0.5711928009986877, "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_Awe/8801b44604a493e2246c1773989c9317c41d53e0e2784f288aac2be049e7b9a4.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "88217e2be61bd79fe39fbfb0bf4a484515d6a9a1eb98bad53a3483c488210289", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "35e6d6210c12a12071d5963ff89986740fd293b57c15bb530aa66bf2bc4ce6ea", "generation_seconds_batch": 23.80236785695888, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.098973274230957, "target_z": 4.718749684952866, "ce": 5.613565921783447, "genuineness": 4.344170093536377, "identity": 0.6482466459274292, "hypothesis": "La puerta sigue abierta. He dejado tu abrijo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/88217e2be61bd79fe39fbfb0bf4a484515d6a9a1eb98bad53a3483c488210289.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "8870dfbed070122d666f2f87efe808c2c18a8555de23cc92b05b0c0caa340cef", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "cd1284fbda13f9978a2c68be55e284f3e42f729e080b0463039a5f6bd12409af", "generation_seconds_batch": 17.993706298060715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6166553497314453, "target_z": 1.18750006212197, "ce": 6.205295085906982, "genuineness": 4.519899368286133, "identity": 0.3379349112510681, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het Oute Raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/8870dfbed070122d666f2f87efe808c2c18a8555de23cc92b05b0c0caa340cef.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": "889131ce75c4b624e6b6a26aefdfcebd678f0d42de6df09d4f49d9c91cbc524e", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "5dfe9741667f8247c5f314efa0c197836399098c84c2b1409cc7ccf9ab072517", "generation_seconds_batch": 24.739027956034988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4037269353866577, "target_z": 3.0625001508676415, "ce": 5.824047088623047, "genuineness": 4.632867813110352, "identity": 0.6721087098121643, "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": 0.120000000000001, "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_Awe/889131ce75c4b624e6b6a26aefdfcebd678f0d42de6df09d4f49d9c91cbc524e.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "89d98b4cca3c8711f8891e6c42bfb4b5088e648232dd2460e445db10f1b532ba", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3bb712513dadcfc9e6e4b26417954979f744e968c781631ff21c3691f85f3eae", "generation_seconds_batch": 18.164114561048336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8888509273529053, "target_z": 1.8359375632312909, "ce": 6.197352409362793, "genuineness": 4.381826400756836, "identity": 0.5461554527282715, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/89d98b4cca3c8711f8891e6c42bfb4b5088e648232dd2460e445db10f1b532ba.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "8a97c45f163e1332398dab69c9844d36a1af0ee586283a19069ffddfc7b1e4bd", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "af80a3345204c5cb913460f5c182a5e176da73cf0bdb79f7f87ed6a6b6b46d87", "generation_seconds_batch": 23.227530956966802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06857477128505707, "target_z": -0.11816406291599534, "ce": 6.133810997009277, "genuineness": 4.262581825256348, "identity": 0.7694435715675354, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/8a97c45f163e1332398dab69c9844d36a1af0ee586283a19069ffddfc7b1e4bd.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "8b105b2cc3e69f189fb307134ac82290c71c9d957985c2989bc5ef36482273a3", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd611e30d075ebaddadf74ac6c03a76a49399e231321e79de3e76e31d772833b", "generation_seconds_batch": 17.559982331003994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49695485830307007, "target_z": 0.9023437483360187, "ce": 6.117925643920898, "genuineness": 4.20609712600708, "identity": 0.2520627975463867, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/8b105b2cc3e69f189fb307134ac82290c71c9d957985c2989bc5ef36482273a3.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "8b3090f40926aefa538ff2b30bbde5f10b71015c19f593435b0cb7bb1c482645", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "9b4f579b6bf27f9177b8e772773765fce68358a8bb2212a6974d321bedb02c63", "generation_seconds_batch": 25.28146181302145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9773964881896973, "target_z": 2.0468750909643134, "ce": 6.419747352600098, "genuineness": 4.243753433227539, "identity": 0.5617608428001404, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/8b3090f40926aefa538ff2b30bbde5f10b71015c19f593435b0cb7bb1c482645.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "8bde5ad4e3a49927b0471bcfff27cb1ca742633d7b6434334e2ce2555d8ab3a3", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5181a8ae1464b01aab5959c627d93c3f0050b7a3ca91b0bd90aeb515760918ff", "generation_seconds_batch": 20.922795415041037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7185555696487427, "target_z": 3.8125001863659103, "ce": 5.7684478759765625, "genuineness": 4.243753433227539, "identity": 0.44483450055122375, "hypothesis": "La puerta sigue abierta. he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/8bde5ad4e3a49927b0471bcfff27cb1ca742633d7b6434334e2ce2555d8ab3a3.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "8c01f3500fcee079be4fe0577f0753226813296092c04eec13879867fda640e3", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "329a30a9a6b88e14d0cb60973c707a192cf4471798191d90bac44fa0c60f4c5f", "generation_seconds_batch": 22.245586121920496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10792835056781769, "target_z": -0.02441405847871176, "ce": 6.340320587158203, "genuineness": 4.7081804275512695, "identity": 0.4824899435043335, "hypothesis": "Die Tür 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_Awe/8c01f3500fcee079be4fe0577f0753226813296092c04eec13879867fda640e3.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "8c6ad895d2e8204a24ff5b8922980d05f55cfa2f18f1d6889e991d6432725fae", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5bd103478cb40f962322a5c40d105db997a2c5c97fb40d37dab1c4a7ab8772f6", "generation_seconds_batch": 23.36996362998616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36577627062797546, "target_z": 0.5898437572105858, "ce": 6.197352409362793, "genuineness": 4.425758361816406, "identity": 0.674431562423706, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/8c6ad895d2e8204a24ff5b8922980d05f55cfa2f18f1d6889e991d6432725fae.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": "8ca2f9f5d1036a4f031b5e53f0b0bafd91d902fc7fd35258e58efc2ee3d9101e", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The keys are on the kitchen table.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b28f9d7278a2457c51fbf68757c2a4e8e43542ab613c91f13ab1bc5c57c96c4b", "generation_seconds_batch": 17.01249683299102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3119019269943237, "target_z": 2.8437501641794922, "ce": 6.157639026641846, "genuineness": 4.21237325668335, "identity": 0.611473023891449, "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_Awe/8ca2f9f5d1036a4f031b5e53f0b0bafd91d902fc7fd35258e58efc2ee3d9101e.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "8cd2f62aa22145366c32010f31786809d122829fd19fba5128f0f743b00aa921", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b8cbce382b1d2138d596b482ddcecdaa17f2df754dc5414ce4ed851a76d3aeb1", "generation_seconds_batch": 23.631710937945172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6267304420471191, "target_z": 3.593749915691612, "ce": 6.443574905395508, "genuineness": 4.607763767242432, "identity": 0.3627094626426697, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/8cd2f62aa22145366c32010f31786809d122829fd19fba5128f0f743b00aa921.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": "8d0637dd7c30e645ee18dceb20c9724e6d11e90510ee120cb3daf1d996db02c3", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d5dacdf5de9d838e01185af192291b0ab4e05be40240cf679421f43bbeead3d3", "generation_seconds_batch": 17.219452708028257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8759697675704956, "target_z": 4.187499920128896, "ce": 6.09409761428833, "genuineness": 4.507347106933594, "identity": 0.8369364738464355, "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_Awe/8d0637dd7c30e645ee18dceb20c9724e6d11e90510ee120cb3daf1d996db02c3.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "8d0c7e68164e13ddba2e4c5b67e0a71b68fb16231eb70e510cd188514048c8f4", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2e7b335b6e4866cd8df86432b535b23f2ededd5a49bfb3699aea8769ef8af41a", "generation_seconds_batch": 22.822796534048393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3840501308441162, "target_z": 3.015625113150731, "ce": 5.839932441711426, "genuineness": 4.570107460021973, "identity": 0.7202268838882446, "hypothesis": "J'ai trouvé la 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_Awe/8d0c7e68164e13ddba2e4c5b67e0a71b68fb16231eb70e510cd188514048c8f4.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": "8d4d15f2332184cfd06239d42a3ac926e2e8e705986a7fccb9d2b9846a55e09a", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Someone moved the little blue chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bfb830f4b1ffbcb8ab83de5de8f2cec2fa8f520679c8b58cbc4a6b2a9ad4ac75", "generation_seconds_batch": 17.110324237961322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6953625082969666, "target_z": 1.3750000709965373, "ce": 6.252951145172119, "genuineness": 4.331617832183838, "identity": 0.5177081823348999, "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_Awe/8d4d15f2332184cfd06239d42a3ac926e2e8e705986a7fccb9d2b9846a55e09a.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "8d9f838bc1798a7f16de35ad4c17518f6484b10fb4f234667e2149a0604dedf9", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "724ce6b7b16960d4231cae22d877c8339e9fd78f1b6e46f732f5301ae5fd1665", "generation_seconds_batch": 25.718000852968544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30018696188926697, "target_z": 0.4335937261496008, "ce": 6.41180419921875, "genuineness": 4.432034492492676, "identity": 0.3955753445625305, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/8d9f838bc1798a7f16de35ad4c17518f6484b10fb4f234667e2149a0604dedf9.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "8dce6e58611bf8cdc73b71e45af196a8809b58b38962f41f48c6bb0edaa66452", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "454edf0be19ff644ef1fde81a8191a0c77466343104dd618edb058ce96d26400", "generation_seconds_batch": 21.922971515916288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.295741319656372, "target_z": 5.18750006212197, "ce": 6.125868320465088, "genuineness": 4.394378662109375, "identity": 0.5100992918014526, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/8dce6e58611bf8cdc73b71e45af196a8809b58b38962f41f48c6bb0edaa66452.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "8ed6710a6f563022483471b3b928123691c9cf2946349b90aeae7c0f7b6febc7", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e42dd68db11f0983e63f78b22ad5a1463848fbe6e4570c6950ff201c1f9bda45", "generation_seconds_batch": 24.11358663800638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3805338442325592, "target_z": 0.6249999645017313, "ce": 6.022613525390625, "genuineness": 4.896461486816406, "identity": 0.7194647789001465, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/8ed6710a6f563022483471b3b928123691c9cf2946349b90aeae7c0f7b6febc7.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "8ee192d4bc8f75ac977613bb38b9ab48a808b55bee7bed2c9145144a09e42ba4", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "6861c78e6a964dc2e33b56a3a13b6088734ce6a2ddc74f2d590ce9a7b1633c06", "generation_seconds_batch": 24.605119501939043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4494026005268097, "target_z": 0.7890624545178433, "ce": 6.1894097328186035, "genuineness": 4.7834930419921875, "identity": 0.3848334550857544, "hypothesis": "Die Tür 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_Awe/8ee192d4bc8f75ac977613bb38b9ab48a808b55bee7bed2c9145144a09e42ba4.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "8f46fec509c6fb6addbbbc9722bd537af185b27a0bcb5a869b506e950e8f8551", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "1caf4bf759185a3373f951c42d0719ff32625b7fc4efed591847d6db275dd87d", "generation_seconds_batch": 21.277143208077177, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6002579927444458, "target_z": 1.1484374833601867, "ce": 6.23706579208374, "genuineness": 4.7081804275512695, "identity": 0.5115370750427246, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.120000000000001, "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_Awe/8f46fec509c6fb6addbbbc9722bd537af185b27a0bcb5a869b506e950e8f8551.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "8f667230b63cf51d364290efa7b8dab72688217c5823c425dcefd9b8444f4d5b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "603621ee8c3a2447189a7a42371f2f28f195dfc23fc074afd359bd7457b2d3c8", "generation_seconds_batch": 22.805094340001233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2895286977291107, "target_z": 0.40820309255236387, "ce": 6.213237762451172, "genuineness": 4.482243061065674, "identity": 0.7813273668289185, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/8f667230b63cf51d364290efa7b8dab72688217c5823c425dcefd9b8444f4d5b.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "907d51252f6fc773a221a03aa39c2e719089ea5e0ef1b8e05fcc3ea38fefed65", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c30cb465deb726442576ba8f16b513ce413dd0fd22cb5e3deaa90d3d3da13210", "generation_seconds_batch": 24.080585200106725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32478296756744385, "target_z": 0.4921875232957388, "ce": 6.086154937744141, "genuineness": 4.833701133728027, "identity": 0.7895771265029907, "hypothesis": "J'ai trouvé la 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_Awe/907d51252f6fc773a221a03aa39c2e719089ea5e0ef1b8e05fcc3ea38fefed65.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "9165e6e4382060718fdc801167b0e4db6d7036fc2cdd758256681026f994f5e0", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "dab6653e4386c9fba0e94173dd4d8186d4f1fefe75c51a37ea290e4dbbfa1bf0", "generation_seconds_batch": 28.647992874030024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5838606953620911, "target_z": 1.1093750465914776, "ce": 5.621508598327637, "genuineness": 4.532451152801514, "identity": 0.6177365183830261, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise dis-moi, quand tu es prêt", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/9165e6e4382060718fdc801167b0e4db6d7036fc2cdd758256681026f994f5e0.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": "91eb068ae7e3368a547795538ebd767c56d13cf5b91fc9eb84904db1f74c81b1", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4d5349775bdb2a0fe3147f296486018930c3b2c95ce3cde2f554386440f525a9", "generation_seconds_batch": 17.526757068932056, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7710269689559937, "target_z": 3.9375000976202386, "ce": 6.125868320465088, "genuineness": 4.243753433227539, "identity": 0.3544933795928955, "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_Awe/91eb068ae7e3368a547795538ebd767c56d13cf5b91fc9eb84904db1f74c81b1.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "9229471383ae86f4643b64f991dccf3d5d0e9fcef32edcbc0815f1d0f816823c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "fdfdf428bd585f904879e51fa61845ec7be035f058673bfc764e22ee3ad2f5be", "generation_seconds_batch": 25.179308898979798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.177680492401123, "target_z": 4.906249835820508, "ce": 5.816103935241699, "genuineness": 4.356721878051758, "identity": 0.49807116389274597, "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_Awe/9229471383ae86f4643b64f991dccf3d5d0e9fcef32edcbc0815f1d0f816823c.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "924c01abce7db5b0c4406510b3efca92240c491d768e611f1a1f2dcd308a8fb6", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fdc3836407ed776bfb81cf40287fa9f2a1bfc1a1a75039b6118fe5088c9c16cd", "generation_seconds_batch": 25.283767410903238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6691268086433411, "target_z": 1.312500115369373, "ce": 6.197352409362793, "genuineness": 4.557555198669434, "identity": 0.5669951438903809, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/924c01abce7db5b0c4406510b3efca92240c491d768e611f1a1f2dcd308a8fb6.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "92620a53c77950aa438d5fafc26159ea91293ea477a0084c51044645f687ec52", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "573c8ccc428a13896659b9842ad5ac0f6ba6488b53402eb4099a10af3c33a80c", "generation_seconds_batch": 16.379619634943083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0101910829544067, "target_z": 2.1249999645017312, "ce": 5.871703147888184, "genuineness": 4.400654315948486, "identity": 0.45470333099365234, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/92620a53c77950aa438d5fafc26159ea91293ea477a0084c51044645f687ec52.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "92721593a6dffd72b149e0e6e3403d567b821e8db092b9e8745c5414c1d128e2", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "778d248b4e2db6f308e3cc83548ed155c1c8adc8e12fb009badd79f19bfa2ace", "generation_seconds_batch": 27.920442400034517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8298205733299255, "target_z": 1.6953125920736343, "ce": 5.927301406860352, "genuineness": 4.632867813110352, "identity": 0.7633249759674072, "hypothesis": "J'ai trouvé la 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_Awe/92721593a6dffd72b149e0e6e3403d567b821e8db092b9e8745c5414c1d128e2.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "92c3aa1b947f66cb8c01d548e508cbf65cf1cb276ff4d5047a602c2fd43acbac", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ddda3de862803aebe07776b980c221a4646c83da10985b666b4d50f16dab2815", "generation_seconds_batch": 23.98678141005803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2004001140594482, "target_z": 2.5781251397744325, "ce": 6.117925643920898, "genuineness": 4.6956281661987305, "identity": 0.6874262094497681, "hypothesis": "J'ai trouvé la 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_Awe/92c3aa1b947f66cb8c01d548e508cbf65cf1cb276ff4d5047a602c2fd43acbac.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "939a96009219e36d03af2be08c4f08f5ff8027937e63d3a3cf9d6dbc88188c5e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "06d0ef9888a3615539c976404cd0a3df11492f2c3a286492c5a5af46806163f5", "generation_seconds_batch": 23.98678141005803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0823392868041992, "target_z": 2.2968749134729705, "ce": 6.340320587158203, "genuineness": 4.68307638168335, "identity": 0.7882912158966064, "hypothesis": "J'ai trouvé la 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_Awe/939a96009219e36d03af2be08c4f08f5ff8027937e63d3a3cf9d6dbc88188c5e.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "93d2252099553d75b71e214dfc3818373dc57a38dbc6c439b09213d66c335a49", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e11ac362d9018e484e4a1010f35856bc1151a28728be2b8c2101c824eb7d3a4f", "generation_seconds_batch": 25.179308898979798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.492509126663208, "target_z": 5.656249871318776, "ce": 6.252951145172119, "genuineness": 4.413206577301025, "identity": 0.2978321611881256, "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_Awe/93d2252099553d75b71e214dfc3818373dc57a38dbc6c439b09213d66c335a49.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "941980474d8d7c30c3621dd44844eda8003ff0b9946e0de7fa47d7d5153ff1cc", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "54cc1b63d882e57b82ea1b8d25bf07fb1b2d9b88758464792dfeb54165198d1a", "generation_seconds_batch": 24.113063510973006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4037269353866577, "target_z": 3.0625001508676415, "ce": 6.356205940246582, "genuineness": 4.375550270080566, "identity": 0.4652101397514343, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/941980474d8d7c30c3621dd44844eda8003ff0b9946e0de7fa47d7d5153ff1cc.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "949e325c0ac19b8225c830c0d1094bec1b62fd4e3437f3b2000fb3f4e7f5a8ad", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6806a9f19c13113274d2277d72c5db2651bdd360faceb266058e967231013648", "generation_seconds_batch": 23.21514641493559, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9249250292778015, "target_z": 1.9218750377169105, "ce": 5.903473377227783, "genuineness": 4.469690799713135, "identity": 0.49072518944740295, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/949e325c0ac19b8225c830c0d1094bec1b62fd4e3437f3b2000fb3f4e7f5a8ad.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "94c834217e5e35476fec43221c1a39ebf94ab9124a8838511b47f94d780ae829", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "2febe6539cf8500e5a0f8ddabab74040d0ad1d27669cec08a2e25678a268665d", "generation_seconds_batch": 18.852255712030455, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3971679210662842, "target_z": 3.046874948971239, "ce": 6.141753673553467, "genuineness": 4.607763767242432, "identity": 0.4880602955818176, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/94c834217e5e35476fec43221c1a39ebf94ab9124a8838511b47f94d780ae829.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "95948907fe483a0c4135179f8e9c0bcfe6433d24eac45689c0e96c98de8096a8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "62d80fb3f62ae31167b8f2f6da3d7e4e919a703beebf62bc4893566ef7787d32", "generation_seconds_batch": 26.622485192958266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7379955649375916, "target_z": 1.476562605385485, "ce": 6.157639026641846, "genuineness": 4.519899368286133, "identity": 0.6625949144363403, "hypothesis": "J'ai trouvé la 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_Awe/95948907fe483a0c4135179f8e9c0bcfe6433d24eac45689c0e96c98de8096a8.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": "960840e46a917d4dfcfa392a5f4de60667c3ebd27239a43e959c6d155ac26220", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ad8b37581f90ef29a620eeae68f55cae8ed2ed24a9b880fe4c14b35a4d375eff", "generation_seconds_batch": 15.657913833972998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1282519102096558, "target_z": 2.4062501908031937, "ce": 6.046441555023193, "genuineness": 4.68307638168335, "identity": 0.5897617340087891, "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_Awe/960840e46a917d4dfcfa392a5f4de60667c3ebd27239a43e959c6d155ac26220.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "965320284f279ff9cfe99908a5cbf76185d6f40f259ba826071e022ceb24e63e", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "6f3bc65f2fcce5779d7a445202a1d043bba1d66e85a8c2ffb75657a69643d657", "generation_seconds_batch": 18.58682055491954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.941322386264801, "target_z": 1.9609376164786938, "ce": 6.4912309646606445, "genuineness": 4.419482707977295, "identity": 0.5034761428833008, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/965320284f279ff9cfe99908a5cbf76185d6f40f259ba826071e022ceb24e63e.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "96978157022b7472f81f2ca418ac9116eaf08f4e1c9417a91aa163f22a836716", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "47ad50fb213dd5884f37e76812d3d02e3c20b6609d97894c6a571fd11b74908d", "generation_seconds_batch": 23.60745233600028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0364267826080322, "target_z": 2.1874999201288956, "ce": 6.38797664642334, "genuineness": 4.632867813110352, "identity": 0.521955668926239, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/96978157022b7472f81f2ca418ac9116eaf08f4e1c9417a91aa163f22a836716.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": "96abc735923718822a015dbdf4f9e66bbde8d2369a680231eab80202a64cee80", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "e1f16f77839ea7edbee2763cc3afba28e51df2d35e453cb95d8cdaad90ade3bd", "generation_seconds_batch": 24.113045021076687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2200769186019897, "target_z": 2.625000177491343, "ce": 5.935244083404541, "genuineness": 4.645420074462891, "identity": 0.5750621557235718, "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": 0.120000000000001, "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_Awe/96abc735923718822a015dbdf4f9e66bbde8d2369a680231eab80202a64cee80.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "96b899f06c5fe8547500e1f20bfbecb30ee8c774de013fc5d5faaeddefcbd00e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b5ec402b147bb8dedafbb26416cc461b985a6de5a55ff9237070239a0cb067e1", "generation_seconds_batch": 23.886877520009875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6068169474601746, "target_z": 1.1640625432635148, "ce": 6.1020402908325195, "genuineness": 4.20609712600708, "identity": 0.3105422854423523, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/96b899f06c5fe8547500e1f20bfbecb30ee8c774de013fc5d5faaeddefcbd00e.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": "980638b6a019a9fc17c10e335be85a92545f430a25a369e705d634b5b84f7e66", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "101fcc39b824d99754d02b95e7aab51d09d0c6b83e043a9ce5e40d59ff4d40fc", "generation_seconds_batch": 15.612214984023012, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14523226022720337, "target_z": 0.06445312361334889, "ce": 5.935244083404541, "genuineness": 4.507347106933594, "identity": 0.7985820770263672, "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_Awe/980638b6a019a9fc17c10e335be85a92545f430a25a369e705d634b5b84f7e66.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "98aa8363606ef86f3f7246a56b86a3fe10fb486ce6609e1170f6a5baeee30281", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "6753b0bef3d935f42cf6a4bff9b35f8ab8dea48cdc8d927dbcc568b1ae386ecc", "generation_seconds_batch": 15.898681996040978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17638717591762543, "target_z": 0.13867187416800933, "ce": 6.24500846862793, "genuineness": 4.833701133728027, "identity": 0.7172334790229797, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/98aa8363606ef86f3f7246a56b86a3fe10fb486ce6609e1170f6a5baeee30281.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "98efabd3ea97de1189e2fe031b44ba96c4187d716deb118c6a9a4750ecc0da19", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bca4774e82162b4444be732ac4e0d96c017521802be197e5ca12b845664de38c", "generation_seconds_batch": 23.469370484002866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9839553833007812, "target_z": 2.0625000088745673, "ce": 6.046441555023193, "genuineness": 4.394378662109375, "identity": 0.4248766303062439, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/98efabd3ea97de1189e2fe031b44ba96c4187d716deb118c6a9a4750ecc0da19.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "9906bdca854a0bff5937a8496a1fa36eb0ea51547142e9fe7414d319865c0555", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "69c505da0d2a35614c909bc0b1b4140e9a1e47725ca099ee968b66781364d311", "generation_seconds_batch": 23.91493258997798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.243269920349121, "target_z": 5.062500150867642, "ce": 5.998785495758057, "genuineness": 4.394378662109375, "identity": 0.6078459024429321, "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_Awe/9906bdca854a0bff5937a8496a1fa36eb0ea51547142e9fe7414d319865c0555.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "994d863f83d4134ec07ef9d8ce28e7147ea765d92c4221833b3edfa6b654a191", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d12560b97929606a00e952dc56f33e306cf5184f1c4ad76199e5f9e4bf716e7a", "generation_seconds_batch": 19.28655435994733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5283465385437012, "target_z": 3.359375011093209, "ce": 6.252951145172119, "genuineness": 4.3881025314331055, "identity": 0.6081472635269165, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/994d863f83d4134ec07ef9d8ce28e7147ea765d92c4221833b3edfa6b654a191.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "9955af52af823b9a3f60b672e9f391c8c2b819ad7781e18dcebfbc25c70a65de", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "43a37df5dba057821b5646fe8f4631287fa1506357bd1e64134e719a25db2087", "generation_seconds_batch": 17.761393680004403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45760127902030945, "target_z": 0.8085937438987351, "ce": 6.324435234069824, "genuineness": 4.13078498840332, "identity": 0.41600632667541504, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/9955af52af823b9a3f60b672e9f391c8c2b819ad7781e18dcebfbc25c70a65de.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "42d7fc292249e01afeb8a43c8982f93a179a175da7e4f0e0247e4baf1ecb551e", "generation_seconds_batch": 15.923801847035065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21820035576820374, "target_z": 0.2382812583199067, "ce": 6.213237762451172, "genuineness": 4.7332844734191895, "identity": 0.6430480480194092, "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_Awe/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "99c7840f06a4efb4d5d879380ce2c5e2aa327150b61f00284f511ccef967c0df", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f6a59ce821370f7f7f96bcb4af68b4e29f006ef8f3e7f9bbbae40c5823c560bf", "generation_seconds_batch": 17.474869732977822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14318259060382843, "target_z": 0.05957030126812595, "ce": 6.117925643920898, "genuineness": 4.356721878051758, "identity": 0.5356448888778687, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/99c7840f06a4efb4d5d879380ce2c5e2aa327150b61f00284f511ccef967c0df.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "99da5bced6d8b599c72c50805ec262d608f150b4a1f73ecdec5f713312f3fb72", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d02962ef387cc5df11b8ba71179bfa5500961fa4450cc866598cc4ce9acc8dcc", "generation_seconds_batch": 25.266896513989195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2501751482486725, "target_z": 0.3144531591116175, "ce": 6.23706579208374, "genuineness": 4.406930446624756, "identity": 0.7425497770309448, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/99da5bced6d8b599c72c50805ec262d608f150b4a1f73ecdec5f713312f3fb72.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "9a05a9dbd578f301230fae571d6cda1b04a5023904b0c040cdd7b923cc43bbbb", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "59e652f0ce53fa433fdd288404e3d724828f77946567892e8b7d9e62ce224d4a", "generation_seconds_batch": 23.549126597936265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8724535703659058, "target_z": 1.7968749844695076, "ce": 6.197352409362793, "genuineness": 4.507347106933594, "identity": 0.39965271949768066, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/9a05a9dbd578f301230fae571d6cda1b04a5023904b0c040cdd7b923cc43bbbb.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "9b0bddd91722e41808453466840d841f27c30332a4f96813466027ebb28f8051", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "28e02aaceebbc4024c9a74e34e1e6bd0ddc8e40d810c39591965ecfe9c7587dd", "generation_seconds_batch": 24.2679460500367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20549243688583374, "target_z": 0.20800783787571545, "ce": 6.316492557525635, "genuineness": 4.557555198669434, "identity": 0.7881989479064941, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/9b0bddd91722e41808453466840d841f27c30332a4f96813466027ebb28f8051.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "9b410620f25a8922889162087e7d2ad72def844e9bbb9462409a822c63442bcf", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4506a3162af6ab59fbb103d3f93db0c0bb0a61a5290cd57b4e80073fc721e152", "generation_seconds_batch": 24.009547177003697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.947881281375885, "target_z": 1.9765625343889477, "ce": 6.181467056274414, "genuineness": 4.7458367347717285, "identity": 0.7456080317497253, "hypothesis": "J'ai trouvé la 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_Awe/9b410620f25a8922889162087e7d2ad72def844e9bbb9462409a822c63442bcf.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": "9b4ed7fdc8648e8a9336f95ed5e351daacb0e53d344acbfe5650f690c4056070", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "44f4f97f1c48a554d073d1f580282a6f840e38b6619887e839654697418260aa", "generation_seconds_batch": 23.491155444993638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.269505500793457, "target_z": 5.124999822508657, "ce": 5.935244083404541, "genuineness": 4.381826400756836, "identity": 0.41856271028518677, "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_Awe/9b4ed7fdc8648e8a9336f95ed5e351daacb0e53d344acbfe5650f690c4056070.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "9b5efd9326cea867b9c0fbc40f13044c4ff41175cf7901a636affcbcf54cb438", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "6b25d27effe2a426d6cd7fbb5158edbf39a11938cf7ed27d070bcceae6ece911", "generation_seconds_batch": 23.21514641493559, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1544876098632812, "target_z": 2.468750146430358, "ce": 6.133810997009277, "genuineness": 4.632867813110352, "identity": 0.58041912317276, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/9b5efd9326cea867b9c0fbc40f13044c4ff41175cf7901a636affcbcf54cb438.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "9b89393648bd716fb52ff3e04ad91046099a54062088b27febd0bebaba289a24", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "82a82258a08b1315601ec72881ca0cb3f82403d6352409207c8bcb170e90639c", "generation_seconds_batch": 24.339841037988663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2266358137130737, "target_z": 2.640625095401597, "ce": 5.847874641418457, "genuineness": 4.425758361816406, "identity": 0.3628378212451935, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/9b89393648bd716fb52ff3e04ad91046099a54062088b27febd0bebaba289a24.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "9bcaeece8c82ba329ad53d086a250a39cf5fae5113cc8bf6b73340a4b18e85ab", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b6fd4950b9b4b3e9188217a9826cda5d4c8a8fc5924be7ae1c2e6249da3d84f", "generation_seconds_batch": 18.282097978051752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22967848181724548, "target_z": 0.26562500665592537, "ce": 5.959072113037109, "genuineness": 4.394378662109375, "identity": 0.2376338541507721, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/9bcaeece8c82ba329ad53d086a250a39cf5fae5113cc8bf6b73340a4b18e85ab.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "8b797b36114a39dc9e7cff52ee413eb5503064b9ad6c9741777d2080edaf30bf", "generation_seconds_batch": 17.82224960392341, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05668671056628227, "target_z": -0.146484377495972, "ce": 6.332377910614014, "genuineness": 4.494794845581055, "identity": 0.5340734720230103, "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_Awe/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "9c68f83962f68258c8d4b26e8c08a621332ff3c328d1bcbfc8747f0cb8df5220", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7315a98faab34bd3af98a9a1d6793a22751a4f2e2dfe45c6da9e0ae56d22ff7f", "generation_seconds_batch": 23.794955478981137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0036321878433228, "target_z": 2.1093750465914773, "ce": 6.268836498260498, "genuineness": 4.494794845581055, "identity": 0.44108477234840393, "hypothesis": "The 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_Awe/9c68f83962f68258c8d4b26e8c08a621332ff3c328d1bcbfc8747f0cb8df5220.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "adbd38b56dfc8aec38011bb219a9b8fcf6a015b6f534242454542e1f78dd709a", "generation_seconds_batch": 20.61316282406915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14646205306053162, "target_z": 0.06738279572152148, "ce": 6.062326908111572, "genuineness": 4.457139015197754, "identity": 0.7469700574874878, "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_Awe/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "9d0c727d966e1df3a1f7024fe95d889370d15704b3f7ed9c0bfc2d329e8a7003", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "cf8f1b6fa874780b2a697c332e32636ac65c220e42cdc70282c78b9930bd00e6", "generation_seconds_batch": 24.231034388998523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4248066246509552, "target_z": 0.7304687283682426, "ce": 5.5817952156066895, "genuineness": 4.482243061065674, "identity": 0.42168647050857544, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/9d0c727d966e1df3a1f7024fe95d889370d15704b3f7ed9c0bfc2d329e8a7003.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "9d0e22240bfda25ccf16ced2a1a0794bdba2fb8d29980b42ec113c6a4be3127e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "85d7bca36dd4d69f94fd275d6b13289fa89d482d66b0de56ce0821602f1da792", "generation_seconds_batch": 23.794955478981137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43300530314445496, "target_z": 0.7500000177491343, "ce": 6.09409761428833, "genuineness": 4.419482707977295, "identity": 0.47861140966415405, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/9d0e22240bfda25ccf16ced2a1a0794bdba2fb8d29980b42ec113c6a4be3127e.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "9d2962416dd8bb6752a59491e2d7702f42e7b83be1046b7b49fcfcf4870387ee", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "769490706bf0dc5835c3459933c4e97602d66a07686dac0c5ea4da4b8504c9a6", "generation_seconds_batch": 21.274989960016683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19524410367012024, "target_z": 0.1835937616478694, "ce": 6.1020402908325195, "genuineness": 4.457139015197754, "identity": 0.757195234298706, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/9d2962416dd8bb6752a59491e2d7702f42e7b83be1046b7b49fcfcf4870387ee.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "9d3e39fc2cc42849377103526c54850a1d72b1be9d7ad34702a1ca327e68436f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "521a8c5c8c90388829544bfa38cb70fc9c028eb50e71325d941c198c2de5d64c", "generation_seconds_batch": 26.508791313972324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30182671546936035, "target_z": 0.43750002662370147, "ce": 6.109982967376709, "genuineness": 4.758388519287109, "identity": 0.6266101002693176, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/9d3e39fc2cc42849377103526c54850a1d72b1be9d7ad34702a1ca327e68436f.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "9e53756549319283054a12f37d2813f94e1e8db4435efbd23ca99128a59df054", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4db5632d1de2d1e2cd915401ec55032f47a3b82b4063485498105ae0d2c20fad", "generation_seconds_batch": 24.78261285298504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8265410661697388, "target_z": 1.687499991125433, "ce": 6.4912309646606445, "genuineness": 4.494794845581055, "identity": 0.5530740022659302, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/9e53756549319283054a12f37d2813f94e1e8db4435efbd23ca99128a59df054.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "9e9eddbf39b9c80e5d1d4e4f81ac37c025eb91c1285f3b67751acf737a68da2b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "50f1586fa8d46c73b8ac5d886244f1057cd268d8800eac218ce29be34a07c043", "generation_seconds_batch": 17.054319567978382, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4854767322540283, "target_z": 0.875, "ce": 6.1894097328186035, "genuineness": 4.7834930419921875, "identity": 0.7276380062103271, "hypothesis": "Die Tür 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_Awe/9e9eddbf39b9c80e5d1d4e4f81ac37c025eb91c1285f3b67751acf737a68da2b.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "9f31ba55bac232d7f11fca7b2271aba3729a184548a87f24209b1ed232c4b026", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "d37a8676ebb6f4bcc1178c0c77bcf6fadbd30143f627e34707dde55537f937af", "generation_seconds_batch": 23.916014860966243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2528715133666992, "target_z": 2.703125051028761, "ce": 6.054384231567383, "genuineness": 4.7332844734191895, "identity": 0.739061176776886, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/9f31ba55bac232d7f11fca7b2271aba3729a184548a87f24209b1ed232c4b026.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "9f909f071956d0dca28c7f904e7db37581f381decb9db6266f4862572e970083", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "fbe3aa7c9e2874b16737bb4b037952742752e3fca2c0e41d4f480c4c59f3afdf", "generation_seconds_batch": 22.540899846004322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13006474077701569, "target_z": 0.028320323454543828, "ce": 6.181467056274414, "genuineness": 4.256305694580078, "identity": 0.5353358387947083, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/9f909f071956d0dca28c7f904e7db37581f381decb9db6266f4862572e970083.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "a004fd02f1c7cf145e8cbe338af763a318ec24e876ab096aa1105d1a0e912516", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "cdd047e0ef39d3d90dbae4eff46b882780a937ca3c326b6e77bd48ad4b7cf8ba", "generation_seconds_batch": 24.364194937981665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06365557014942169, "target_z": -0.12988282234522294, "ce": 6.070269584655762, "genuineness": 4.507347106933594, "identity": 0.6777780652046204, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/a004fd02f1c7cf145e8cbe338af763a318ec24e876ab096aa1105d1a0e912516.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "a0797c8391b62fd2c1b80545875646843acfffd7c7815a2b0b4b6ba5ad3da704", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "17a6c548e0f798326ec306c5266fcc778362d6d2aa5d29ce1f2409103fa853e1", "generation_seconds_batch": 25.805361568927765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49695485830307007, "target_z": 0.9023437483360187, "ce": 6.1894097328186035, "genuineness": 4.557555198669434, "identity": 0.6618841290473938, "hypothesis": "J'ai trouvé la 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_Awe/a0797c8391b62fd2c1b80545875646843acfffd7c7815a2b0b4b6ba5ad3da704.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "a07bd8628c101f95892010ee0291ddd4b30d2359078f99ae790233551eed1938", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "5868f336f9345728eabe2b97f7dda44758403cc121796a8e30363c00eee0c53b", "generation_seconds_batch": 24.33819666004274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16121965646743774, "target_z": 0.10253907400920427, "ce": 6.109982967376709, "genuineness": 4.7081804275512695, "identity": 0.5823360681533813, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.120000000000001, "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_Awe/a07bd8628c101f95892010ee0291ddd4b30d2359078f99ae790233551eed1938.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "a0ae6bec60d6e627a984ef16a8b4a68f8abd3bff18595bb075a6fcc19578124f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5a99312902254d021b22087cf0745dc3abb399e2bc01d7a441d770e378fc9e3a", "generation_seconds_batch": 23.706010808004066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1413697004318237, "target_z": 2.4375000266237015, "ce": 5.903473377227783, "genuineness": 4.557555198669434, "identity": 0.41391250491142273, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/a0ae6bec60d6e627a984ef16a8b4a68f8abd3bff18595bb075a6fcc19578124f.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "a0efbdc3f9ff887367fa7ce3ae558a35b025bb51ad63af06ef63fa49a9e0318d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b3600a3a5aa7055775389dd84ddae4a116a7ea82c90acdb695e4dd81bb1cecbc", "generation_seconds_batch": 23.471134782070294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8855714797973633, "target_z": 1.828125104276164, "ce": 6.213237762451172, "genuineness": 4.507347106933594, "identity": 0.622750997543335, "hypothesis": "J'ai trouvé la 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_Awe/a0efbdc3f9ff887367fa7ce3ae558a35b025bb51ad63af06ef63fa49a9e0318d.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": "a1a16765b84e446439995676e2a2530ea8f84570c05096aafbcc3d4ab7c7921b", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Your message arrived after I had left.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "faac95a13ce62202f96f33798d6f94adf154a581ad42cefa5504ba711583fdca", "generation_seconds_batch": 17.85030231496785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3379008173942566, "target_z": 0.5234375011093209, "ce": 6.205295085906982, "genuineness": 4.231201171875, "identity": 0.4241741895675659, "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_Awe/a1a16765b84e446439995676e2a2530ea8f84570c05096aafbcc3d4ab7c7921b.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "a1f106e1140c51c1798c91bfb7927bf2309cd20e9e34c0939513c05152e8b699", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "734c0048378fd9da1a63730d1ea811d7fa77a0e9ac84c1754dfb109b195194f3", "generation_seconds_batch": 17.446112751029432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5740222930908203, "target_z": 1.0859375277330223, "ce": 6.348263263702393, "genuineness": 4.770940780639648, "identity": 0.6113390326499939, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/a1f106e1140c51c1798c91bfb7927bf2309cd20e9e34c0939513c05152e8b699.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "a244082468751547f9dfc737ac8b146e5fcccf000b077eabdf375eb6e6f0aeed", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "e87a2c434c6466ea219a32a7183fccc03cc2003c55be55894e6b9119a300b63c", "generation_seconds_batch": 32.32070487795863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9773964881896973, "target_z": 2.0468750909643134, "ce": 6.356205940246582, "genuineness": 4.7081804275512695, "identity": 0.6679813861846924, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/a244082468751547f9dfc737ac8b146e5fcccf000b077eabdf375eb6e6f0aeed.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "a2b8cfc5068d98410da56e80548627678ea24ee0cf37d89e9dfda806789624a7", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b64715f39759b73914fcd48a00c2ccae4dafbd077571482a88aae023079547f0", "generation_seconds_batch": 17.806292160064913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7251144647598267, "target_z": 3.828125104276164, "ce": 6.165581703186035, "genuineness": 4.7458367347717285, "identity": 0.3986300826072693, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/a2b8cfc5068d98410da56e80548627678ea24ee0cf37d89e9dfda806789624a7.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": "a2c90c838f24be4193408dafb1a3cc70a27df1643093ddefab1a453f368557fc", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "93aa266d69ac76bf80464eefe29bc71800bdea7015c1a627eda40e69a0c40239", "generation_seconds_batch": 18.066441425005905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5018740892410278, "target_z": 0.9140625787617834, "ce": 6.117925643920898, "genuineness": 4.7081804275512695, "identity": 0.5969151258468628, "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_Awe/a2c90c838f24be4193408dafb1a3cc70a27df1643093ddefab1a453f368557fc.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "a2eda8b9e3744f8f443e97584231d531af03407cd2ddffadc7634a3b233b61fb", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "5f58e724046199b2ad4520d3839cc1736c0045f93a94709976276409235aba52", "generation_seconds_batch": 24.46243580104783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9183661341667175, "target_z": 1.9062501198066566, "ce": 6.070269584655762, "genuineness": 4.758388519287109, "identity": 0.7035495638847351, "hypothesis": "La porte est encore ouverte j'ai posé ton manteau sur la chaise dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/a2eda8b9e3744f8f443e97584231d531af03407cd2ddffadc7634a3b233b61fb.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "a3b7b207d255c5985ad88be133288548b475e6ec090a35b3ec016205ca641a16", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "65da239a0a508c75ce3c934f2da8bd7db21585045261ab47767af0c12bd06a0e", "generation_seconds_batch": 22.404613318038173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5936990976333618, "target_z": 1.1328125654499328, "ce": 6.109982967376709, "genuineness": 4.344170093536377, "identity": 0.4724067747592926, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/a3b7b207d255c5985ad88be133288548b475e6ec090a35b3ec016205ca641a16.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "a43639cd89681ceb417c57d3228285bcf93aa30ed4e8165ba9fca8d86ff9772c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "a699c54dce934d94b4bfcc31f9dfcf601802c59993f6200176bc2bf0fb10f449", "generation_seconds_batch": 18.20650086493697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0495446920394897, "target_z": 2.218750039935552, "ce": 6.443574905395508, "genuineness": 4.557555198669434, "identity": 0.4989203214645386, "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_Awe/a43639cd89681ceb417c57d3228285bcf93aa30ed4e8165ba9fca8d86ff9772c.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": "a4e8bcfae303ebcf956219fbce12c44d4acb6e2e9378e537a63b4890429c3a5b", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I wrote the number on the envelope.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "55a365ca6e82841e1022f1fcb3be65d70caa53c2fb0a0bad2774b22d78a82ead", "generation_seconds_batch": 15.948158833896741, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2641128599643707, "target_z": 0.34765625166398134, "ce": 6.149696350097656, "genuineness": 4.18726921081543, "identity": 0.36153796315193176, "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_Awe/a4e8bcfae303ebcf956219fbce12c44d4acb6e2e9378e537a63b4890429c3a5b.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "a4e91bce20b400462fa017bbac6fa232014a8cc45ea2c454a362cf2d3578ac02", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d23ddb7548babfe2b01e1960d32d63b83efd71200136d39bdb700c9fd4ee5b2a", "generation_seconds_batch": 23.315608681063168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1610465049743652, "target_z": 2.484375064340612, "ce": 6.1020402908325195, "genuineness": 4.557555198669434, "identity": 0.5067672729492188, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/a4e91bce20b400462fa017bbac6fa232014a8cc45ea2c454a362cf2d3578ac02.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "a4fc8d01dee044eed155eac771d97e8fc8b0c35ea9d537ab2ef3675dfbdf2984", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9c34f0873655d7665be64db9175f23df352d748c97fc310eaa8b62e09b432c9d", "generation_seconds_batch": 28.293835307005793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1807233095169067, "target_z": 2.5312501020575224, "ce": 5.919358730316162, "genuineness": 4.494794845581055, "identity": 0.38194340467453003, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime, ¿cuándo estás listo?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/a4fc8d01dee044eed155eac771d97e8fc8b0c35ea9d537ab2ef3675dfbdf2984.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "a4ff270dd8414b925fa3925a01ccc8015bcdfee2ce422c5cd5965c6b993fc99a", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a96c01e918dfed1d16b9e2c960b50eca53081616634ba2d067ae81fa595203a4", "generation_seconds_batch": 24.33819666004274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08579196035861969, "target_z": -0.07714844041196735, "ce": 6.300607204437256, "genuineness": 4.68307638168335, "identity": 0.5999552607536316, "hypothesis": "Die Tür 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_Awe/a4ff270dd8414b925fa3925a01ccc8015bcdfee2ce422c5cd5965c6b993fc99a.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "a5412b381627b6388876ba853107e0fb5eed2cc1f6fdd601cd52a3fb654fe5cd", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "efc1a56b16a927d18efc8e7906778ebe2bb601c5157bf12a7c4d37a89a7bc0c5", "generation_seconds_batch": 24.749223783030175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7513501644134521, "target_z": 3.890625059903328, "ce": 6.0146708488464355, "genuineness": 4.557555198669434, "identity": 0.5002004504203796, "hypothesis": "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_Awe/a5412b381627b6388876ba853107e0fb5eed2cc1f6fdd601cd52a3fb654fe5cd.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "a56ffa2909e530212cf010b03ac462cb3e5a887633d682af768a09c7f48c717c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8b148657d145289afd90f090bd92429cb5189a35a922dc90929e0a1d07468aa7", "generation_seconds_batch": 26.41349039308261, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30018696188926697, "target_z": 0.4335937261496008, "ce": 6.197352409362793, "genuineness": 4.507347106933594, "identity": 0.2910839021205902, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/a56ffa2909e530212cf010b03ac462cb3e5a887633d682af768a09c7f48c717c.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "a57edbc6b1868913d3edd6829dc16a7be1179dc264076cc6829dd7ceaaf53daf", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "306d4a1b683fc85769475b93d242141cfa076a4d9cba96a6e137b0cac88278e2", "generation_seconds_batch": 22.459649711032398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7445544600486755, "target_z": 1.4921875232957387, "ce": 6.213237762451172, "genuineness": 4.281409740447998, "identity": 0.5290539264678955, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/a57edbc6b1868913d3edd6829dc16a7be1179dc264076cc6829dd7ceaaf53daf.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "a5ae115f67f87431dadb2596180d7708edc6db30f6e7db9e68db64f82bcd6de7", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0975e0f7f30e79915840b0e2bd16e36aa3e825cce58e1cd3912072eb4e43fef3", "generation_seconds_batch": 21.479282796033658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05340724438428879, "target_z": -0.1542968808239347, "ce": 6.356205940246582, "genuineness": 4.557555198669434, "identity": 0.6111246943473816, "hypothesis": "Die Tür 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_Awe/a5ae115f67f87431dadb2596180d7708edc6db30f6e7db9e68db64f82bcd6de7.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "a5c3181e9d091997609f92765db143c3de924a2521aad881533ff00da877d1bb", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f2883e3d92f308f91f02d14baf5ccd6592756d8179de341bdce9f735468bb273", "generation_seconds_batch": 23.936594696016982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4461231529712677, "target_z": 0.7812499955627165, "ce": 6.141753673553467, "genuineness": 4.369274139404297, "identity": 0.6426494717597961, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/a5c3181e9d091997609f92765db143c3de924a2521aad881533ff00da877d1bb.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": "a63759604af128ff2f3a9dbc1fce014255786fb76b4b79f010a540cfa7ccac90", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4773aaaeb7846e4609905268aca692c9424455e336756bd4afb31df6c89055e8", "generation_seconds_batch": 24.113045021076687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3906090259552002, "target_z": 3.031250031060985, "ce": 5.657250881195068, "genuineness": 4.406930446624756, "identity": 0.25382834672927856, "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_Awe/a63759604af128ff2f3a9dbc1fce014255786fb76b4b79f010a540cfa7ccac90.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "a69de94eab18fc406b61af022424086947ba7da8fa7ff6d669ec743d459c6ee4", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fc466c4296c61f834fba5aed106cb093fbbb829eb2e7d71de657b6ff09cee351", "generation_seconds_batch": 17.468123214086518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.859335720539093, "target_z": 1.7656250066559254, "ce": 6.213237762451172, "genuineness": 4.7834930419921875, "identity": 0.7913641929626465, "hypothesis": "J'ai trouvé la 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_Awe/a69de94eab18fc406b61af022424086947ba7da8fa7ff6d669ec743d459c6ee4.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "8e504f5d4e7ba240401cef9fb49571f942647a493b2975fcb2108f8d34310ad6", "generation_seconds_batch": 18.091744463075884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030041061341762543, "target_z": -0.20996093486536288, "ce": 6.23706579208374, "genuineness": 4.18099308013916, "identity": 0.6342044472694397, "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_Awe/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "a9455ce69fff8bf891555280f8a10e868540384e85946d2692a5945d79f35d9b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4b540972978a8ec099d6f479b77d83a864ba375036510d7570dcb3b56e2f13a4", "generation_seconds_batch": 24.1981374330353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2856661081314087, "target_z": 2.781249924566179, "ce": 6.356205940246582, "genuineness": 4.375550270080566, "identity": 0.43321096897125244, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/a9455ce69fff8bf891555280f8a10e868540384e85946d2692a5945d79f35d9b.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ac254eb3bbe6d7160f7a65b0aaae2b64b1778ada919fc800e23070a047f94e5c", "generation_seconds_batch": 19.15486834803596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10546875, "target_z": -0.03027343819332556, "ce": 6.149696350097656, "genuineness": 4.469690799713135, "identity": 0.7259457111358643, "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_Awe/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "a99a9d5002187e44e7eba2bea8775adc7b0a83e6b78e3446b709ff2e24d12339", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "c6349321d5bb7de072b4fcdf45a861b3ad751333e357aea81267b994c59c3691", "generation_seconds_batch": 22.768610117956996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45924100279808044, "target_z": 0.8124999733762985, "ce": 6.356205940246582, "genuineness": 4.425758361816406, "identity": 0.5054309368133545, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/a99a9d5002187e44e7eba2bea8775adc7b0a83e6b78e3446b709ff2e24d12339.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "a9cba8456db6231aba58c4e25f2076f2ac41ea02abff64ca4ec6b3437a178183", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6050b42243c6cb9a35912dbb81cfa611d967463c170c64d159e07563c9cccc53", "generation_seconds_batch": 24.787387477932498, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4824340343475342, "target_z": 3.250000017749134, "ce": 6.316492557525635, "genuineness": 4.344170093536377, "identity": 0.26399075984954834, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/a9cba8456db6231aba58c4e25f2076f2ac41ea02abff64ca4ec6b3437a178183.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "a9ce836b959ca044a0b0569dc9ecdcbd3140f30b21ad6df6f16cf4ddf0e1d3e2", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "f1ffde1dca73e561dee1fcb93dabd99674887463efee2713be76a8cf64d5849f", "generation_seconds_batch": 24.46243580104783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2952677607536316, "target_z": 0.42187496672037317, "ce": 5.597680568695068, "genuineness": 4.68307638168335, "identity": 0.8524978160858154, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/a9ce836b959ca044a0b0569dc9ecdcbd3140f30b21ad6df6f16cf4ddf0e1d3e2.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "aa13eb013e939afc092b5f933967861d694a90122256cdcf7b40077e70315d2d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "65ba9b9b82c6bf295b203f206b1250d1af140e8e11d4888a8af3cc3ad50082b1", "generation_seconds_batch": 22.629602925037034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3182240426540375, "target_z": 0.4765625343889477, "ce": 6.173524379730225, "genuineness": 4.281409740447998, "identity": 0.4018048346042633, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/aa13eb013e939afc092b5f933967861d694a90122256cdcf7b40077e70315d2d.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "aa279a272282c038e6ef209e9da37ad91d22673ba4eb7373d309ee718095cf2f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4cf14233b9c2716c631db9225a1d6904f9e2ee996c29e02a884bb8c4b7074f6f", "generation_seconds_batch": 24.03958803298883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5576249361038208, "target_z": 1.0468749489712388, "ce": 5.95112943649292, "genuineness": 4.243753433227539, "identity": 0.184099018573761, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/aa279a272282c038e6ef209e9da37ad91d22673ba4eb7373d309ee718095cf2f.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "aa584f636295a9667afce4766486ecedcae77ec9cb1c915d642eee630baa030c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "aa33ec7b426f54708d3061373005a91768e989818931442367d32a53978d9761", "generation_seconds_batch": 24.03220355103258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8265410661697388, "target_z": 1.687499991125433, "ce": 5.903473377227783, "genuineness": 4.005263805389404, "identity": 0.45144227147102356, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/aa584f636295a9667afce4766486ecedcae77ec9cb1c915d642eee630baa030c.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "ab007042529a9b1780d8fc02beb4e4d8bf054b0f16aed24c136267e33713dfc9", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2626bf511dbb79309894effc00e1ea255c0b7d4507bd5a910238bff53d959098", "generation_seconds_batch": 23.4675678339554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9642786383628845, "target_z": 2.015625113150731, "ce": 6.38797664642334, "genuineness": 4.344170093536377, "identity": 0.4308778643608093, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ab007042529a9b1780d8fc02beb4e4d8bf054b0f16aed24c136267e33713dfc9.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "ab463e6757d55adce45a9a340ee2f4bd80cd0379f7cb544a239ad61252de03cf", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "68d18402bf8cfe1e98246886c5ea99bdd3b63ba83ac6ffe70142617adc6e2436", "generation_seconds_batch": 24.11358663800638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2739512622356415, "target_z": 0.37109377052243653, "ce": 5.935244083404541, "genuineness": 4.821148872375488, "identity": 0.670993447303772, "hypothesis": "La porte est encore ouverte j'ai posé ton manteau sur la chaise dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ab463e6757d55adce45a9a340ee2f4bd80cd0379f7cb544a239ad61252de03cf.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c7aee21a000cc0bc3a5c4ec1127eee0ed5a2cf614344144439f69920b2da7694", "generation_seconds_batch": 20.311453656991944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17228785157203674, "target_z": 0.12890626497583207, "ce": 6.467403411865234, "genuineness": 4.243753433227539, "identity": 0.3511834740638733, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "ab978e9c77baccf9bb7d7ce0506a8dca226efc3c67e16e7df630b8f2b38f6db8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "aad21886859f54f12c67c43144d64a6d1cc9fe46205da8ad0567ef117bf2d388", "generation_seconds_batch": 16.933239127974957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.058326445519924164, "target_z": -0.1425781213947071, "ce": 6.252951145172119, "genuineness": 4.545003414154053, "identity": 0.6612914800643921, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ab978e9c77baccf9bb7d7ce0506a8dca226efc3c67e16e7df630b8f2b38f6db8.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "ab9a217230485b6b6e88dd37c6ce7c934bb05eff8ed578c1219df6c9a2d0240f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aa83c4bc83e17c904f308f91b2b3ec76b131ebdc1b49fe1b59d725301d01acd6", "generation_seconds_batch": 19.067096341983415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7347160577774048, "target_z": 1.4687500044372837, "ce": 6.157639026641846, "genuineness": 4.607763767242432, "identity": 0.7405673861503601, "hypothesis": "J'ai trouvé la 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_Awe/ab9a217230485b6b6e88dd37c6ce7c934bb05eff8ed578c1219df6c9a2d0240f.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "abf4428d914419af46c2e4451c1473a84b568e4aaac52ac12c38f5b3b80ed1aa", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b34e691064b9cc63aeb915d34e6f9e4f105ebdf77f92b3f94d0500fecc4f483a", "generation_seconds_batch": 17.603876461973414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36741599440574646, "target_z": 0.5937499866881493, "ce": 6.340320587158203, "genuineness": 4.6203155517578125, "identity": 0.527865469455719, "hypothesis": "ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/abf4428d914419af46c2e4451c1473a84b568e4aaac52ac12c38f5b3b80ed1aa.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "ac1b27510ad6f303f67f82fd370a40406c376ae052ea53c6e71e0bfda9f462f0", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "121d98cdbceb91a3dd512829eebd9bb94c85dd3b0e5205f6c5514abf2fe959ba", "generation_seconds_batch": 23.667781451018527, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0429857969284058, "target_z": 2.2031251220252983, "ce": 6.046441555023193, "genuineness": 4.419482707977295, "identity": 0.413128137588501, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ac1b27510ad6f303f67f82fd370a40406c376ae052ea53c6e71e0bfda9f462f0.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": "ac4a97e81fab3c59b24f394eea4ddc18a779c28a64eb62769ccee4e243199436", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0ae6a7360cd9d5fd02f88d82de169c1a3002bb6afa1cf19c043d038d6ea86ff4", "generation_seconds_batch": 18.95370879303664, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3578144311904907, "target_z": 2.953125157523567, "ce": 5.871703147888184, "genuineness": 4.406930446624756, "identity": 0.7481217384338379, "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_Awe/ac4a97e81fab3c59b24f394eea4ddc18a779c28a64eb62769ccee4e243199436.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "ad2f01fd589880df0fb00eeb61979b4b037505bef7d9f2b55ec59fa121d91e56", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3d088e9a5ddac2d088b636422a35e0eac4c1b6f2bd22f390313f0f27e9c6f1fd", "generation_seconds_batch": 17.97626573208254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17064811289310455, "target_z": 0.125, "ce": 6.173524379730225, "genuineness": 4.268857479095459, "identity": 0.30005764961242676, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ad2f01fd589880df0fb00eeb61979b4b037505bef7d9f2b55ec59fa121d91e56.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "ad4200a9a9b8c5719a7198bd91a8f48cc303c901786f3d9d10c8525794104a0d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "16fe7b2a39f0fa6765ad2dc3087e06894dad0425067dc23185bbfad0d2a2046b", "generation_seconds_batch": 23.91493258997798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.02026629447937, "target_z": 4.531250102057522, "ce": 6.221180438995361, "genuineness": 4.507347106933594, "identity": 0.5491765141487122, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ad4200a9a9b8c5719a7198bd91a8f48cc303c901786f3d9d10c8525794104a0d.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "ad5ddae10e17781506b3597fe599326bac2439570884c7e1b041e7d924d43d5b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "173b56cc3fdd5d9e0fbe5c367e759ff94a0175102a811123a7ef55705579966d", "generation_seconds_batch": 21.625705752987415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3559378683567047, "target_z": 0.5664062383521307, "ce": 5.998785495758057, "genuineness": 4.331617832183838, "identity": 0.44328463077545166, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ad5ddae10e17781506b3597fe599326bac2439570884c7e1b041e7d924d43d5b.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5a4aa3c1a51fd6fd67eb58cdb81b363b0f7826ce8d659ae2467a2986c3d00a05", "generation_seconds_batch": 17.305806210031733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08702176064252853, "target_z": -0.07421875055466044, "ce": 6.340320587158203, "genuineness": 4.3504462242126465, "identity": 0.742285966873169, "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_Awe/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "1fe0c829db1cea218468af626ac1994411a4e43c0b795a0b73f1c8148420a100", "generation_seconds_batch": 17.553265613969415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08989129215478897, "target_z": -0.06738281347065578, "ce": 6.41180419921875, "genuineness": 4.080576419830322, "identity": 0.34253567457199097, "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_Awe/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "ae485cc40c20a6eb1c8dca903b928bdae89e746a509082cd6ef2e433fd9ac50d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e0b879986b3ff1df01719695107efac2f75eb4712e809b0eda69d952cf0bbbea", "generation_seconds_batch": 24.01047313201707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.90524822473526, "target_z": 1.875, "ce": 6.252951145172119, "genuineness": 4.632867813110352, "identity": 0.8151141405105591, "hypothesis": "J'ai trouvé la 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_Awe/ae485cc40c20a6eb1c8dca903b928bdae89e746a509082cd6ef2e433fd9ac50d.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "aea09028557386f7921b64841ae9af55e767809b0a486f5f5b8b8f8c6d8d6868", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "66b9c04ecbec9ca7e8e7a37ea7c6f9f807b63218709191c21e415e911994bd9b", "generation_seconds_batch": 21.168359369970858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.518744945526123, "target_z": 5.718750110932089, "ce": 6.149696350097656, "genuineness": 4.369274139404297, "identity": 0.335868239402771, "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_Awe/aea09028557386f7921b64841ae9af55e767809b0a486f5f5b8b8f8c6d8d6868.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": "aeb7b143b8c367f2ee86efcfe002d5fc7b3ac5bc804c29f9ea2fd35a4fc09f1a", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "08c0221396359c5fc72484463bb7df4f70fdf8e64a53416face1d91369cca784", "generation_seconds_batch": 17.29291858104989, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1413697004318237, "target_z": 2.4375000266237015, "ce": 5.80021858215332, "genuineness": 4.532451152801514, "identity": 0.441622793674469, "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": 0.120000000000001, "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_Awe/aeb7b143b8c367f2ee86efcfe002d5fc7b3ac5bc804c29f9ea2fd35a4fc09f1a.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": "aefa6a4d60adeb948dd69a7f9d74772a64957ea8e95de5b2bbf0b5332894cb20", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2ed54d9be4fa1ffcaf2734eb3f8241603ecf27ba3b4144bd17a4d4fe04ff9c20", "generation_seconds_batch": 17.387452155002393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0823392868041992, "target_z": 2.2968749134729705, "ce": 5.967014789581299, "genuineness": 4.356721878051758, "identity": 0.5019147992134094, "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_Awe/aefa6a4d60adeb948dd69a7f9d74772a64957ea8e95de5b2bbf0b5332894cb20.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "af10d2c86ab20b1e8c5ea3d87f7628618405f9ef002fa7fefc3557ffe6378337", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "f69734db1dba14006685376b2d66048b22cc26a220efbc800e6584ffff94eaf1", "generation_seconds_batch": 24.14861163997557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2870691120624542, "target_z": 0.40234374833601866, "ce": 6.260893821716309, "genuineness": 4.68307638168335, "identity": 0.5370854139328003, "hypothesis": "Die Tür 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_Awe/af10d2c86ab20b1e8c5ea3d87f7628618405f9ef002fa7fefc3557ffe6378337.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "af21215cb354bf6e797154458782209e5010fdebe0d2649fd138fb2f828cc15c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "296d7fa7518bb2c9decbc4a650e7db4e4ce59d22648eab753b21920f79f876b6", "generation_seconds_batch": 17.179644610965624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21902021765708923, "target_z": 0.24023437305868844, "ce": 6.109982967376709, "genuineness": 4.821148872375488, "identity": 0.7640596032142639, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/af21215cb354bf6e797154458782209e5010fdebe0d2649fd138fb2f828cc15c.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "af3c577922063d8fc1a61f6c87acc56bc8f39cc4474bfbac4ec2e60909770944", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "36f64659904f5b2533ad5f2120496d7e7df4dc11c008409362e77dc5e724fcfe", "generation_seconds_batch": 24.445872443029657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6363321542739868, "target_z": 1.2343750998388805, "ce": 6.467403411865234, "genuineness": 4.356721878051758, "identity": 0.4224008619785309, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/af3c577922063d8fc1a61f6c87acc56bc8f39cc4474bfbac4ec2e60909770944.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "af7d474ebf8fbb7e39607a487a77f5dc66e899380715dc6c9bdf75d21942e5c0", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4d27177d3bbc5bbdbcc35e5cb3426490d8d27e0f511e8a75c110ff05b8c2ebc2", "generation_seconds_batch": 23.907403483986855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.171877920627594, "target_z": 0.1279297076064412, "ce": 6.165581703186035, "genuineness": 4.18099308013916, "identity": 0.6324812173843384, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/af7d474ebf8fbb7e39607a487a77f5dc66e899380715dc6c9bdf75d21942e5c0.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "af894da453353bc174f7a788e9ae1178402cf378b14074d91061bc835e864d98", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "931d4618d88e5f6b703d69d66a04b9d9f7cc75d25549b71c8d48611402c8ccee", "generation_seconds_batch": 21.168359369970858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.426919937133789, "target_z": 5.5000001242439405, "ce": 5.998785495758057, "genuineness": 4.331617832183838, "identity": 0.5263946056365967, "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_Awe/af894da453353bc174f7a788e9ae1178402cf378b14074d91061bc835e864d98.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": "af8f851035ae851967efe83b04d73bd5643bbdbcc3a05cf03e4570fc0336c52f", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e15078d00bcb99bceedd25896c54458c072cbe4af1123fccff60204f14aad7bf", "generation_seconds_batch": 18.37517802102957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07677343487739563, "target_z": -0.09863280903337221, "ce": 6.3641486167907715, "genuineness": 4.482243061065674, "identity": 0.7480803728103638, "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_Awe/af8f851035ae851967efe83b04d73bd5643bbdbcc3a05cf03e4570fc0336c52f.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "afa5fd4c9429b4e219dc88c6c9ce19220493d1098e10741692f1a066611072ee", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4141d466a437c7d9d798da5e41eca84f498e8d79ff7e391e7eda6afeb46b22fa", "generation_seconds_batch": 18.282097978051752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08743169158697128, "target_z": -0.07324219318526959, "ce": 5.621508598327637, "genuineness": 4.375550270080566, "identity": 0.3512154221534729, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/afa5fd4c9429b4e219dc88c6c9ce19220493d1098e10741692f1a066611072ee.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "afd9b050132b203b402e68b09395e0e16302282b5d1e9fff3939e88408cb2b60", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b7dd8694437db0fce1b8e4ee779e1f537ae9e147ef2a7e103e91adb1031274b4", "generation_seconds_batch": 18.20650086493697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5414644479751587, "target_z": 3.3906251308998656, "ce": 6.467403411865234, "genuineness": 4.432034492492676, "identity": 0.3626384139060974, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/afd9b050132b203b402e68b09395e0e16302282b5d1e9fff3939e88408cb2b60.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": "b0c929e40172ff58cfe7623fccb5e90082b78bef41c5ff88ad84161ceb354691", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3a98a306b85fa33751534a41e20e6bc92c5e1a62a610d4b3263cde3de810bcb0", "generation_seconds_batch": 23.393288691993803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0888983011245728, "target_z": 2.312500115369373, "ce": 5.998785495758057, "genuineness": 4.507347106933594, "identity": 0.4347660541534424, "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_Awe/b0c929e40172ff58cfe7623fccb5e90082b78bef41c5ff88ad84161ceb354691.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "b0f281591a2a483192e5db302d268d681202e30318145ea40ddf975237606e09", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c3e7720145413e108eb5fe1b2b31c33392f2363650152e23a3d96f877ff5cbce", "generation_seconds_batch": 26.400119371013716, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25837379693984985, "target_z": 0.333984377495972, "ce": 5.804190158843994, "genuineness": 4.1998209953308105, "identity": 0.667303204536438, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/b0f281591a2a483192e5db302d268d681202e30318145ea40ddf975237606e09.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": "b18fd123fc884bee405b66de9caba49e179477dc562efed12889fdb0ae2665fc", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0a6769619cd1889b01c44c0f1fa5aa6688bae924639c1efe16f240e066055544", "generation_seconds_batch": 17.387452155002393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9577196836471558, "target_z": 2.000000053247403, "ce": 5.967014789581299, "genuineness": 4.457139015197754, "identity": 0.5592539310455322, "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_Awe/b18fd123fc884bee405b66de9caba49e179477dc562efed12889fdb0ae2665fc.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "b2189ebeae9c57db1884b590f26c22199a5275da8d6bae6920a935c16e285207", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "68629225950cb3aa94088283a695b24295361f0649d6c005a2716313d6dbea8f", "generation_seconds_batch": 18.862459311960265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3512554168701172, "target_z": 2.9374999556271644, "ce": 6.205295085906982, "genuineness": 4.645420074462891, "identity": 0.8056689500808716, "hypothesis": "Ah ! 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_Awe/b2189ebeae9c57db1884b590f26c22199a5275da8d6bae6920a935c16e285207.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": "b30db23646ee54f7ade321a72a43635e747103ac90ae3f222bf9c66aebd5544a", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e71a3dcdbbac9ff76ee127634d3265701cc1ed7de547eea53fa7fc454643fac", "generation_seconds_batch": 21.939212242956273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2518148720264435, "target_z": 0.31835938858918095, "ce": 6.260893821716309, "genuineness": 4.570107460021973, "identity": 0.6036200523376465, "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_Awe/b30db23646ee54f7ade321a72a43635e747103ac90ae3f222bf9c66aebd5544a.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "b3cc51ec1dc46be1c88dcc8b7c2be6c47a7a119eff4f3c7f89a03854b4152a24", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "e3fc1fce5361550744bb916483c222cfaa2c2708f27cd5a7cd6f04f70523d340", "generation_seconds_batch": 23.30994353699498, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12022633850574493, "target_z": 0.00488280459608863, "ce": 6.475345611572266, "genuineness": 4.7081804275512695, "identity": 0.5626367926597595, "hypothesis": "Die Tür 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_Awe/b3cc51ec1dc46be1c88dcc8b7c2be6c47a7a119eff4f3c7f89a03854b4152a24.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "b41b9f25118f69cefff75bd6553e1f93c4b90ee62a2bce7bd3547cbfc77c9aed", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ae38b01b763d176e6722a01f164d6176d85e527c3df845b7178d8c288c49c9cf", "generation_seconds_batch": 21.465720435022376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8497340679168701, "target_z": 4.124999964501732, "ce": 5.967014789581299, "genuineness": 4.494794845581055, "identity": 0.5260115265846252, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/b41b9f25118f69cefff75bd6553e1f93c4b90ee62a2bce7bd3547cbfc77c9aed.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "e5c66d5b904b554f27a63be4054e625bfbfe7f27ef5fe4d026a556a560d0a260", "generation_seconds_batch": 16.575160778011195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.058326445519924164, "target_z": -0.1425781213947071, "ce": 6.284721851348877, "genuineness": 4.356721878051758, "identity": 0.7389367818832397, "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_Awe/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "b44e1195fda50f2351d3698b389d62396d69197c8ff5e2c166ba6b6cb510c680", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e07797ff32c27d6d64c823697678398887827a2499d039159d2b9c674955f858", "generation_seconds_batch": 23.81005395599641, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27887046337127686, "target_z": 0.38281252995166415, "ce": 6.141753673553467, "genuineness": 4.256305694580078, "identity": 0.5891721248626709, "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_Awe/b44e1195fda50f2351d3698b389d62396d69197c8ff5e2c166ba6b6cb510c680.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": "b4d679bacb60e60a329e790f7e4f07c52fcd1ba43fbbb89249a0ce71546e5222", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7437a269c9aadeaa2581172163418cd917bc2c6e13cdb5e929aabe2246019363", "generation_seconds_batch": 17.23968708200846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28378963470458984, "target_z": 0.3945312183843545, "ce": 5.927301406860352, "genuineness": 4.20609712600708, "identity": 0.5137079358100891, "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_Awe/b4d679bacb60e60a329e790f7e4f07c52fcd1ba43fbbb89249a0ce71546e5222.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": "b4fadaee8eaeb97f7eb763b47dc2a8569d83c1918f23e2d0ad344dbb3634f288", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "990ec34ddb734e2a2919a14207ba2a5c670db5b8cdf370747c7ddef928c4bef0", "generation_seconds_batch": 23.75709748698864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4313655495643616, "target_z": 0.7460937172750336, "ce": 6.109982967376709, "genuineness": 4.105680465698242, "identity": 0.14399419724941254, "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_Awe/b4fadaee8eaeb97f7eb763b47dc2a8569d83c1918f23e2d0ad344dbb3634f288.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "b5986662096ec6f066eadf53a6017ada7f308777093124f83c2ced91a096acad", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e1256f5fec10d392cc3cc78333f86c6748bd58cebbec41bb7c0be3d16f8b454e", "generation_seconds_batch": 22.87917009193916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3542981445789337, "target_z": 0.5625000088745672, "ce": 5.748591423034668, "genuineness": 4.174716949462891, "identity": 0.45607131719589233, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/b5986662096ec6f066eadf53a6017ada7f308777093124f83c2ced91a096acad.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": "b5bb3621b471e62ecd3cca7b5b4627c981fa74fa2cf0a0fd9b869f784914b7fd", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "ffc894e195e599d5166a8a6b468d16cd81e1dcbb12cfac1426088cd210e27af7", "generation_seconds_batch": 17.37614841503091, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4264463484287262, "target_z": 0.734374957845806, "ce": 6.316492557525635, "genuineness": 4.507347106933594, "identity": 0.5234724879264832, "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": 0.120000000000001, "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_Awe/b5bb3621b471e62ecd3cca7b5b4627c981fa74fa2cf0a0fd9b869f784914b7fd.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "b602f848bc05e0e845b86e3f4276f5119636046994d93e85a4cb99bd8aba7977", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "3bb30f4e2f937c698a91f99cd2331ff058070733e0ae2abdcf122fef612b5e4f", "generation_seconds_batch": 23.963510739966296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2594304084777832, "target_z": 2.718749968939015, "ce": 6.443574905395508, "genuineness": 4.6956281661987305, "identity": 0.3451799750328064, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/b602f848bc05e0e845b86e3f4276f5119636046994d93e85a4cb99bd8aba7977.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "b62c3179232496f68b12be8a09b780d8bc72b22fdc37dd3747e14acdbee008ba", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "024973599776837fd2eeb0cf8c05a7708aade356d40efccd3599fbc25c684b07", "generation_seconds_batch": 18.215019547962584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32232335209846497, "target_z": 0.48632810808285637, "ce": 6.197352409362793, "genuineness": 4.306513786315918, "identity": 0.6798588633537292, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/b62c3179232496f68b12be8a09b780d8bc72b22fdc37dd3747e14acdbee008ba.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "b6e6577ba31ff9afb9cbb408bbca4d20330e8debb489d99019269dbfcf452f4c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2719f8aaf8c6ac336b1b792e2f3ee49032d67d6e602ade3e63db047108862f9c", "generation_seconds_batch": 17.656719321967103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7412750124931335, "target_z": 1.484375064340612, "ce": 6.157639026641846, "genuineness": 4.2249250411987305, "identity": 0.5926805734634399, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/b6e6577ba31ff9afb9cbb408bbca4d20330e8debb489d99019269dbfcf452f4c.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "b6f4874a8c9f5d29bc76aa9172c58e96e1590bed78b1a11cd55c898107c1e899", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4d465ba56b2efe505c15f4569bcf57fb18119bc8462f1943ca37ca9ffefcc553", "generation_seconds_batch": 22.924157557892613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29854723811149597, "target_z": 0.4296874966720373, "ce": 6.268836498260498, "genuineness": 4.256305694580078, "identity": 0.25466880202293396, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/b6f4874a8c9f5d29bc76aa9172c58e96e1590bed78b1a11cd55c898107c1e899.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "b74e8d2572016162b3fde48ff94d5e8f86db054b18d2e339a48f4d220b82216c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e0ac03b3a39f5ae81472dacdafc6533e5fb0bb29b0b7aa229076aa196ee81774", "generation_seconds_batch": 23.64021608699113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24033674597740173, "target_z": 0.2910156402531623, "ce": 6.2767791748046875, "genuineness": 4.595211505889893, "identity": 0.7025701403617859, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt , c'est ce su nœud.", "wer": 0.2222222222222222, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/b74e8d2572016162b3fde48ff94d5e8f86db054b18d2e339a48f4d220b82216c.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "b76a1dd816325f5eb1aa6e2dfcb3434c59275778ca21e99c5cee912e1bbcdded", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7aab488350f94f71758e7fca595498b9fe4a54fcbc6a76571a6bacd9aee5e9c9", "generation_seconds_batch": 24.13139084202703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7972626686096191, "target_z": 4.000000053247403, "ce": 5.967014789581299, "genuineness": 4.406930446624756, "identity": 0.5807706117630005, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/b76a1dd816325f5eb1aa6e2dfcb3434c59275778ca21e99c5cee912e1bbcdded.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "b7d9418a2cd5ff8a25a3dc0ab3f990bb18198324731fa9a71198a9a7d7baff74", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1fd8f65c0929ae075a393e48616b5d23d3d657539083ac4d0d25929f5f1b5b6c", "generation_seconds_batch": 24.365749898017384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4625204801559448, "target_z": 0.8203125033279627, "ce": 6.09409761428833, "genuineness": 4.808597087860107, "identity": 0.8230438232421875, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt, quelle jeune est sans soin.", "wer": 0.2777777777777778, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/b7d9418a2cd5ff8a25a3dc0ab3f990bb18198324731fa9a71198a9a7d7baff74.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "b8e8f82efeb4da9d6565e6a3fb2f4ba54c6b2c26d7fa5c3dd53b299688f7451e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "79cb2777653dc4188117d017261fc8c202e60d9a935d38699fb3817fa49fde12", "generation_seconds_batch": 24.85153456008993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1046488881111145, "target_z": -0.03222655293210729, "ce": 5.967014789581299, "genuineness": 4.632867813110352, "identity": 0.6175013780593872, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/b8e8f82efeb4da9d6565e6a3fb2f4ba54c6b2c26d7fa5c3dd53b299688f7451e.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "b8f64e5244b2a2b7d7c506fcc1e8c671973c87d9bc71bd4cfe68a0081fb5f35d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "f17e4d98d7828317fbf95ea54fa00f7fac3f3257465693cf9401a01cf6f05eb5", "generation_seconds_batch": 24.120961789041758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5773017406463623, "target_z": 1.0937499866881493, "ce": 6.38003396987915, "genuineness": 4.319066047668457, "identity": 0.5755840539932251, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/b8f64e5244b2a2b7d7c506fcc1e8c671973c87d9bc71bd4cfe68a0081fb5f35d.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "b92ab6912a988b7abe0555c02dfe7a51124c0665c3865024501ac543ceecddf0", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "03e1d3b0dfd9b3817f2399bc977ef909bbba142d4c56d2f5bec82e53a4ea3377", "generation_seconds_batch": 24.06023435399402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5231905579566956, "target_z": 0.9648437039631829, "ce": 6.038498878479004, "genuineness": 4.632867813110352, "identity": 0.8198935985565186, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la 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_Awe/b92ab6912a988b7abe0555c02dfe7a51124c0665c3865024501ac543ceecddf0.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "b9628a10c27d94c98b7b5c818382ae2dc13a6aeac293f24f35ce56ba5c996d81", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "234c82d634912506ba340a5b9185b4996ea9bedaa954302eee3ab0dd72e3e1a0", "generation_seconds_batch": 24.75342698104214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3526584208011627, "target_z": 0.5585937793970037, "ce": 6.141753673553467, "genuineness": 4.293961524963379, "identity": 0.5923851132392883, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/b9628a10c27d94c98b7b5c818382ae2dc13a6aeac293f24f35ce56ba5c996d81.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": "b96da1110ffb868df4d8e002c430937e75867400f54c6d98b2536bdd630cc9ea", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "469db899f940c20e33de94d0ba393b2cef68f281c23411427327a9876b68c6b9", "generation_seconds_batch": 24.357626615907066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.112091302871704, "target_z": 4.750000088745671, "ce": 5.808161735534668, "genuineness": 4.6203155517578125, "identity": 0.693618893623352, "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_Awe/b96da1110ffb868df4d8e002c430937e75867400f54c6d98b2536bdd630cc9ea.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "b96fb54bd7fa6430d1a60935aa9de09ec9adf64b1ef67c74a8a3d285595a5832", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c106ee4093caa7a79d768ad3857311aac3b4c9b86a8f7d045f85ea9df2724e7b", "generation_seconds_batch": 28.773778139962815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45432180166244507, "target_z": 0.8007812139470709, "ce": 6.284721851348877, "genuineness": 4.300237655639648, "identity": 0.7445148229598999, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/b96fb54bd7fa6430d1a60935aa9de09ec9adf64b1ef67c74a8a3d285595a5832.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "b99d3fa2bf904d9929c52ebdcc8468bb7599b63db7a8106867790c07cc35d695", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "da53a4d878a993b65f29e3cb8078da5a81497ed7cd2974b0ea0e2927e0e46740", "generation_seconds_batch": 17.9412726869341, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12063627690076828, "target_z": 0.005859379714613799, "ce": 6.332377910614014, "genuineness": 4.582659721374512, "identity": 0.6939130425453186, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/b99d3fa2bf904d9929c52ebdcc8468bb7599b63db7a8106867790c07cc35d695.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "b9ad20defed40aa59bd2355a0336d24243bc0d83e7c5631fe1752d46508bafd8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "de47d4cc27d117b42ff7827b1331414aa788ad6c6f1d24065d944c178abf6314", "generation_seconds_batch": 23.741508404025808, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13334420323371887, "target_z": 0.03613281790793936, "ce": 5.982900142669678, "genuineness": 4.105680465698242, "identity": 0.5668661594390869, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/b9ad20defed40aa59bd2355a0336d24243bc0d83e7c5631fe1752d46508bafd8.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": "ba32363cbb6b13ea0630b19bdbcbd8d89f0afc88ab7602e49bfd379eef1c71ba", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "68e819ada4d3b81a8823a4ab390e8c2feeb13362155828275d88585ea0b57403", "generation_seconds_batch": 24.728964876034297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7511134147644043, "target_z": 1.507812583199067, "ce": 5.974957466125488, "genuineness": 4.7332844734191895, "identity": 0.676654577255249, "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_Awe/ba32363cbb6b13ea0630b19bdbcbd8d89f0afc88ab7602e49bfd379eef1c71ba.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "ba4124ce365b635ba3d0e87d5a2096192e173637262d977c4e9c1d2cdef5153f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "aa2e399aa46941d2ea3d83e4f69113ad500a11394f800836d871d25c46052e46", "generation_seconds_batch": 26.622485192958266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6396116018295288, "target_z": 1.2421875587940074, "ce": 6.1894097328186035, "genuineness": 4.720732688903809, "identity": 0.7549499273300171, "hypothesis": "J'ai trouvé la 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_Awe/ba4124ce365b635ba3d0e87d5a2096192e173637262d977c4e9c1d2cdef5153f.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "dcd641671d9e00777a8368882e573c7eb7737f931438d66c93a87dcd4bd3d962", "generation_seconds_batch": 18.76254422101192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24033674597740173, "target_z": 0.2910156402531623, "ce": 6.197352409362793, "genuineness": 4.645420074462891, "identity": 0.6547081470489502, "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_Awe/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.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": "ba830fbdaf621a227a94ef94045836bea1687a89d220381e6ac4aef83628bbb0", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f481a7ee38d8bcaff428700af6b3875a56ffef493756fe71d9ea12b6a23488c1", "generation_seconds_batch": 17.379140036995523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.007148265838623, "target_z": 4.499999698264717, "ce": 6.054384231567383, "genuineness": 4.319066047668457, "identity": 0.6427679657936096, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ba830fbdaf621a227a94ef94045836bea1687a89d220381e6ac4aef83628bbb0.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "ba9e882d3b1e4c87feb82c13f61e1108f5ee926480d34c0424d290abdf91150b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "73fdf0c97c1eb388d6c8e7a674ee72482688eff8c8a4a27cc9013ca9a0ec7923", "generation_seconds_batch": 23.449394820956513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8103805780410767, "target_z": 4.031250173054059, "ce": 6.292664527893066, "genuineness": 4.557555198669434, "identity": 0.37752214074134827, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ba9e882d3b1e4c87feb82c13f61e1108f5ee926480d34c0424d290abdf91150b.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": "baed63dda067a20989c436504da2b392544dd8ced8447807f25e1a00a0ecab58", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I wrote the number on the envelope.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b07be313b87787792a4c619858fbcdea3db9fbca9e207f24ef9ccc0078a3f431", "generation_seconds_batch": 24.462632821989246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45432180166244507, "target_z": 0.8007812139470709, "ce": 6.046441555023193, "genuineness": 4.300237655639648, "identity": 0.5888875722885132, "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_Awe/baed63dda067a20989c436504da2b392544dd8ced8447807f25e1a00a0ecab58.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "baeee20a42592d0cfdb02f4f36e8a9530e249ab4051876a331920960cb5a328e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a6c918c7a1034f79d20a9dd537e5e97751db87f485f243545931c429b8262e69", "generation_seconds_batch": 23.865435277926736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.151444911956787, "target_z": 4.843750164179492, "ce": 6.284721851348877, "genuineness": 4.507347106933594, "identity": 0.3180397152900696, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/baeee20a42592d0cfdb02f4f36e8a9530e249ab4051876a331920960cb5a328e.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "bb0ec87e9584dc32cd96f19a1c99f720b875f2fd75eb33535493941ad7efda6e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f6893ca44240c0337d0ff2704eb84ab14953ffae211606aa29879718e5474d02", "generation_seconds_batch": 23.261928980937228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9249250292778015, "target_z": 1.9218750377169105, "ce": 5.998785495758057, "genuineness": 4.6203155517578125, "identity": 0.7417526245117188, "hypothesis": "J'ai trouvé la 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_Awe/bb0ec87e9584dc32cd96f19a1c99f720b875f2fd75eb33535493941ad7efda6e.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": "bb71adf3101135ddd3d07740bf27d6a0ee2afc76260b5c447c12db5373b28157", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "199f614803784d6ab53ea60092cd7ae04a4e330e6b7b00b5768424f1c7f6cbda", "generation_seconds_batch": 17.79366643796675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6726430654525757, "target_z": 3.7031251930218354, "ce": 5.967014789581299, "genuineness": 4.570107460021973, "identity": 0.5087521076202393, "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": 0.120000000000001, "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_Awe/bb71adf3101135ddd3d07740bf27d6a0ee2afc76260b5c447c12db5373b28157.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "bbcb6116d2a49c5d141aca0bae9611725eb53ebadbfdd9b8c96faec7104cfc5f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a4f9dfbba11bfeadb1306df7c4113e8aa9daf7611a6fb74fcd3705ffe42b9caa", "generation_seconds_batch": 18.126222689985298, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1923745572566986, "target_z": 0.1767577890655961, "ce": 6.054384231567383, "genuineness": 3.8922953605651855, "identity": 0.33320119976997375, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/bbcb6116d2a49c5d141aca0bae9611725eb53ebadbfdd9b8c96faec7104cfc5f.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "bbe3bc192e66fee2bc975fcfda7a4823a164112ab6aca293ee841b031518c69b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "193e89973a1e1628172cc1a641be601030e8f2e748e117df50be1cded85be165", "generation_seconds_batch": 25.901887829997577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12309587001800537, "target_z": 0.011718741680093295, "ce": 6.221180438995361, "genuineness": 4.344170093536377, "identity": 0.8126723170280457, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/bbe3bc192e66fee2bc975fcfda7a4823a164112ab6aca293ee841b031518c69b.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "bbf00051ba9866413cecb5cc7ee560df789a92310960ea60e0bfc42e71b92942", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "9fb60d88274c0ca9dcb23399ae414cf0fb2e8894ae57b01ece660b721c6547f2", "generation_seconds_batch": 24.903886437998153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4264463484287262, "target_z": 0.734374957845806, "ce": 6.213237762451172, "genuineness": 4.256305694580078, "identity": 0.32779091596603394, "hypothesis": "The 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_Awe/bbf00051ba9866413cecb5cc7ee560df789a92310960ea60e0bfc42e71b92942.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "bc28f5cb2ae6bb1ad65e260660c6d101c4adcbf0d8e02983daf694376e66e39b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4d2f3e17ac91f02d479375ae6ee333896f3417f93ecbd9d3c366c9544da99320", "generation_seconds_batch": 27.271128027001396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26083338260650635, "target_z": 0.3398437217123172, "ce": 6.38797664642334, "genuineness": 4.68307638168335, "identity": 0.6437108516693115, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/bc28f5cb2ae6bb1ad65e260660c6d101c4adcbf0d8e02983daf694376e66e39b.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "bc31950a1ff261e1b14135dbbc462c9217f2bf18a75eaa36f6d306a5c775e082", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "36c2df798dbe649506c43dd6809cfaac34b914c5a9a532c236537f5f6d219d54", "generation_seconds_batch": 17.03526578610763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0954571962356567, "target_z": 2.3281250332796266, "ce": 6.197352409362793, "genuineness": 4.582659721374512, "identity": 0.4805871844291687, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/bc31950a1ff261e1b14135dbbc462c9217f2bf18a75eaa36f6d306a5c775e082.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "bc6b867ff9eede37cebc0e7ee625ce1190f257bdd5aae0a3c167d92cd6e20a59", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bd87d8a354ec6043c6fdeae612dc611c92f1dfacc9fb92990dd44e8bd8c5b715", "generation_seconds_batch": 16.581624803016894, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4494026005268097, "target_z": 0.7890624545178433, "ce": 5.863759994506836, "genuineness": 3.961331605911255, "identity": 0.4142801761627197, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/bc6b867ff9eede37cebc0e7ee625ce1190f257bdd5aae0a3c167d92cd6e20a59.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "bc8d441ecd62802f2c5e4e62a43f00d420f28523b7b2fe9405fbc548f2c4f582", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "8634deafdc7902fde891ef53c4b4e09a480c0b75fa758010728edb6b89214ef5", "generation_seconds_batch": 25.00820851000026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2272188812494278, "target_z": 0.25976562694131156, "ce": 6.173524379730225, "genuineness": 4.770940780639648, "identity": 0.5874741077423096, "hypothesis": "Die Tür 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_Awe/bc8d441ecd62802f2c5e4e62a43f00d420f28523b7b2fe9405fbc548f2c4f582.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "bcdd6f1c3e77ed80076b7a3bf4b3bbec9e08f0915eae75df2378d2c47635af12", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f3de0580afbb2c2be7895574de87c7f29a55660d738ec5fca7395755be102cb5", "generation_seconds_batch": 21.99291931290645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21820035576820374, "target_z": 0.2382812583199067, "ce": 6.252951145172119, "genuineness": 4.570107460021973, "identity": 0.816288948059082, "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_Awe/bcdd6f1c3e77ed80076b7a3bf4b3bbec9e08f0915eae75df2378d2c47635af12.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "bd328d95330ce56c42ceac49b25b213a7343c2ac90b4b1f646e16052d806d371", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "56048020ae38f24039d406289e0066b8631b9be8f13db8913b18497dd3b63861", "generation_seconds_batch": 22.854820701060817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05873637646436691, "target_z": -0.14160156402531623, "ce": 6.2767791748046875, "genuineness": 4.570107460021973, "identity": 0.4558296799659729, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/bd328d95330ce56c42ceac49b25b213a7343c2ac90b4b1f646e16052d806d371.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "bd452e563c20a5f991b318652237fbd56ed0cf4e86e3a3cd228d9294a27ecdca", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "ca4d4d1e7592098c77f3a59bfa93f7e56972745fbd631fca90da08e69cbc8dbd", "generation_seconds_batch": 24.46514968504198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0714443027973175, "target_z": -0.11132812583199067, "ce": 6.141753673553467, "genuineness": 4.720732688903809, "identity": 0.5338153839111328, "hypothesis": "Die Tür 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_Awe/bd452e563c20a5f991b318652237fbd56ed0cf4e86e3a3cd228d9294a27ecdca.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "bd4ac8779ec9261c74183dc0223b669e61f5029cb3209098d02db67ef32d27d7", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e944a86c17d8c0b87b8faa729648acc810e9048d31607b56e77e0046c88ae5ca", "generation_seconds_batch": 23.19738363509532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6002579927444458, "target_z": 1.1484374833601867, "ce": 5.665193557739258, "genuineness": 4.532451152801514, "identity": 0.4533764719963074, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/bd4ac8779ec9261c74183dc0223b669e61f5029cb3209098d02db67ef32d27d7.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "be20b54474eb7829f084caf975367f2c43325c6f3ce99663585ae5c9095775d9", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "bb3464431e4d218d74f468546bec59ff4269f0a7e431d52ea04a0fde791e1ced", "generation_seconds_batch": 24.042862550006248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08579196035861969, "target_z": -0.07714844041196735, "ce": 6.1894097328186035, "genuineness": 4.105680465698242, "identity": 0.3897443115711212, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/be20b54474eb7829f084caf975367f2c43325c6f3ce99663585ae5c9095775d9.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "be3e2f0afc856ef57290a59e13fd4535b0deb0d67baff95908b6e58a4ddb7c6a", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1d842b6becf207b379dae086a6c7beaecded2325197d0f86c5515575c9fffccc", "generation_seconds_batch": 25.00820851000026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6461705565452576, "target_z": 1.2578126186973357, "ce": 6.340320587158203, "genuineness": 4.645420074462891, "identity": 0.3651076853275299, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/be3e2f0afc856ef57290a59e13fd4535b0deb0d67baff95908b6e58a4ddb7c6a.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "be8b5d1a70ba256da4c433a1c7b0843e06e8cd4917f92ae0f0ffe1d5feefc93f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "a8f345be7a6598befb048cee975a8fa50feb97fdc149a416a509a32d5322466c", "generation_seconds_batch": 23.138425928889774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2594304084777832, "target_z": 2.718749968939015, "ce": 6.252951145172119, "genuineness": 4.582659721374512, "identity": 0.6163049936294556, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/be8b5d1a70ba256da4c433a1c7b0843e06e8cd4917f92ae0f0ffe1d5feefc93f.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": "beaddee2ef973352e77da3028e4134e30653f16de40e6fe2a9ab3324e016a549", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc720b6fdcdc513579e54fe6fce5a19bae754384368b6765bd9408941ce1d610", "generation_seconds_batch": 18.37517802102957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06693504005670547, "target_z": -0.1220703101426931, "ce": 6.372091293334961, "genuineness": 4.607763767242432, "identity": 0.6512824296951294, "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_Awe/beaddee2ef973352e77da3028e4134e30653f16de40e6fe2a9ab3324e016a549.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": "bebfa36ead5eb2acb3eac8799ce265f5f57040c3aa1a7dea1e9f2fcfcca063b7", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8e3590cfd2594905f0c410730145cffabd16a190b0672bc293d667a9a295fa13", "generation_seconds_batch": 23.42671022308059, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2739512622356415, "target_z": 0.37109377052243653, "ce": 6.1894097328186035, "genuineness": 4.293961524963379, "identity": 0.3794412910938263, "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_Awe/bebfa36ead5eb2acb3eac8799ce265f5f57040c3aa1a7dea1e9f2fcfcca063b7.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "c00118ec5ee124f989544bf21e7a3adde9014d2f0649dee100efffb99f9a1442", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "30aeed0b957d7bf0a1c88debbec79a22916d6ed697539b9d1f0c4e1097be62e6", "generation_seconds_batch": 22.230071795987897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8366162776947021, "target_z": 4.093750128681224, "ce": 6.403861999511719, "genuineness": 4.557555198669434, "identity": 0.4310176372528076, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c00118ec5ee124f989544bf21e7a3adde9014d2f0649dee100efffb99f9a1442.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": "c0746c033951857c99faecaa6ff8965de497d745944213ea55a41d0561141c8d", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Escribí el número en el sobre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fcc443a89d561e94af5ff412764618dafeb5f99358398a03130e4875b6432e6a", "generation_seconds_batch": 16.888502010027878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8363794684410095, "target_z": 1.710937509983888, "ce": 6.117925643920898, "genuineness": 4.532451152801514, "identity": 0.5572716593742371, "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_Awe/c0746c033951857c99faecaa6ff8965de497d745944213ea55a41d0561141c8d.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "c0dd45f200861ff4d2eafd7e9dca6c7543304b083fb0e7e87d30025cecdfa897", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bb03cc716f58acbec686f7516c1f27cc5ebee44a72a91aa3942e65f7ef96706b", "generation_seconds_batch": 23.57557928597089, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5609044432640076, "target_z": 1.0546875499194401, "ce": 6.133810997009277, "genuineness": 4.532451152801514, "identity": 0.4879758954048157, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c0dd45f200861ff4d2eafd7e9dca6c7543304b083fb0e7e87d30025cecdfa897.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "c10cb39653b19328cf66a131601cf4c1fa756fa1dc28f329e2a85adfd6b5db6e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "13878b8a7f924d6b77b8546f8b83856beacc703218461be963ff919f775c1501", "generation_seconds_batch": 25.95774943905417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14277265965938568, "target_z": 0.05859374389873508, "ce": 6.149696350097656, "genuineness": 4.833701133728027, "identity": 0.7138067483901978, "hypothesis": "La porte est encore ouverte j'ai posé ton manteau sur la chaise dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c10cb39653b19328cf66a131601cf4c1fa756fa1dc28f329e2a85adfd6b5db6e.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "c15e32a9f8781ae304664b61f326ab08274920f0f1f0d6910ec5fecfc0fc89a7", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "cbb7095e9c00e872d8e3d93328e043c53f0685c2cfec687dbb4387cf6da4c1e1", "generation_seconds_batch": 23.78177526697982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23541754484176636, "target_z": 0.27929688082393467, "ce": 5.974957466125488, "genuineness": 4.419482707977295, "identity": 0.7594215869903564, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c15e32a9f8781ae304664b61f326ab08274920f0f1f0d6910ec5fecfc0fc89a7.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "c17bc57dbbe7d1d7348974fffc4eae213021230b1be8c7dc7c0d9e2c45f9a68a", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "626abfbe5e9c1e2a3c3198bb81049ecaa84feeef8437f33bf41a7cffc891a9e4", "generation_seconds_batch": 17.603876461973414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3297021687030792, "target_z": 0.5039062827249664, "ce": 6.252951145172119, "genuineness": 4.356721878051758, "identity": 0.5749614238739014, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c17bc57dbbe7d1d7348974fffc4eae213021230b1be8c7dc7c0d9e2c45f9a68a.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": "c18ffed49c226401430032f1e9c793ccd713fdb275cc440c3cf25f7bfd98ab83", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a27ae488a84e1b84603a7eff6be48dae2243768407b34a0a0556a3567c2dbe75", "generation_seconds_batch": 17.27049375406932, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3446965217590332, "target_z": 2.9218750377169105, "ce": 6.125868320465088, "genuineness": 4.532451152801514, "identity": 0.7325419187545776, "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_Awe/c18ffed49c226401430032f1e9c793ccd713fdb275cc440c3cf25f7bfd98ab83.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "c19e73e6bd3a9025422aefd406f493e886d959ab312e6324e98d568eeeff2139", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "273d6b8c0701a3496f8c67ae4cf4412e9036f6475f3598a2867ecf56613f7e5c", "generation_seconds_batch": 23.817916917963885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11530714482069016, "target_z": -0.006835937084004665, "ce": 6.109982967376709, "genuineness": 4.13078498840332, "identity": 0.2505619525909424, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c19e73e6bd3a9025422aefd406f493e886d959ab312e6324e98d568eeeff2139.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "c1be5195ff40291e6fd9ec38c613ad9a9a9fc9bab2cb099f16c1b19b392b272c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "47712b3a9d49c6ecae955356574ee60b9e169dc07f8849ea76f7527ffee55db8", "generation_seconds_batch": 23.496694679022767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4234037399291992, "target_z": 3.109375188584552, "ce": 6.292664527893066, "genuineness": 4.6956281661987305, "identity": 0.7088627815246582, "hypothesis": "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_Awe/c1be5195ff40291e6fd9ec38c613ad9a9a9fc9bab2cb099f16c1b19b392b272c.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "c1f1de94e63b329fa564210fe0c2d9588161601acbcb1ddb8ed130abd810914b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "300ee6e2adcbf6d9680cb810116ffd75b4f12b07aa335546d208b0993e369cc5", "generation_seconds_batch": 23.895570373977534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3313418924808502, "target_z": 0.5078125122025299, "ce": 6.3641486167907715, "genuineness": 4.362998008728027, "identity": 0.38430750370025635, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c1f1de94e63b329fa564210fe0c2d9588161601acbcb1ddb8ed130abd810914b.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "c289c6db1200684c2f152be76c97b6e88383470feb3caee0329d67d9e72fffb6", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6203cc078bc97a9afddd4ba1a703af1199ed1502bb1121df7b11e405d0db28e7", "generation_seconds_batch": 17.437000641948543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0036321878433228, "target_z": 2.1093750465914773, "ce": 5.677107334136963, "genuineness": 4.394378662109375, "identity": 0.395710289478302, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c289c6db1200684c2f152be76c97b6e88383470feb3caee0329d67d9e72fffb6.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "c2b1b63d008425f1abb5061b7c5bdffdb2a18370ab4738fe7f223ad9b0c942a4", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "66978e5e9e7ec9d7c48ebaa120c7379bba4d0f79f9a897dba61e6ee75eb0a069", "generation_seconds_batch": 24.364194937981665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.052177444100379944, "target_z": -0.1572265706812416, "ce": 6.1894097328186035, "genuineness": 4.381826400756836, "identity": 0.5660397410392761, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c2b1b63d008425f1abb5061b7c5bdffdb2a18370ab4738fe7f223ad9b0c942a4.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "c3039bd7ee61111c38ff3f72143bb5403a4f93f21494c4bb3a005739ee282921", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "cdb81e001ab9a773b18cfe46ab923f3304c4c671fbde3eaebf0cdeeac506053c", "generation_seconds_batch": 24.559872444951907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7707902193069458, "target_z": 1.5546876209159775, "ce": 6.046441555023193, "genuineness": 4.306513786315918, "identity": 0.5674972534179688, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c3039bd7ee61111c38ff3f72143bb5403a4f93f21494c4bb3a005739ee282921.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "c373eb0904c19173603e7c81d99a0a66971a1a407f1da672270b86a6d992387b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "de140dd324541d40756feaa4b6980e17068b61c968c3f2d23ae0cedf71ae6a5b", "generation_seconds_batch": 23.16549112193752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3512554168701172, "target_z": 2.9374999556271644, "ce": 6.340320587158203, "genuineness": 4.3127899169921875, "identity": 0.2897559404373169, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c373eb0904c19173603e7c81d99a0a66971a1a407f1da672270b86a6d992387b.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "287ffe86115dfb9567c8ea951d66374860a5bf550dc44fd2d78fa9b24a7cd2ee", "generation_seconds_batch": 20.61316282406915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5117124319076538, "target_z": 0.9374999556271643, "ce": 5.959072113037109, "genuineness": 4.469690799713135, "identity": 0.6363500356674194, "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_Awe/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.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": "c3c847d415c84601b4a8d38713d8637dfc56d5e8b319049a775e125a8f1b098f", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9978f486d19079f730549d51814de534e1c360c515669384b6a38b5cfb2376c6", "generation_seconds_batch": 17.381291800993495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6232143044471741, "target_z": 1.2031251220252983, "ce": 6.229123115539551, "genuineness": 4.494794845581055, "identity": 0.40213868021965027, "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_Awe/c3c847d415c84601b4a8d38713d8637dfc56d5e8b319049a775e125a8f1b098f.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "c41817851b7888d315a16d940de283f33dddba6a2e3660dac1d90b9573c16b6f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "caf58a1ff8d43b3941dd903b890e4bf1c665d2bc2803f32bbd59a045878dd113", "generation_seconds_batch": 21.885285104974173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08866149187088013, "target_z": -0.07031250332796268, "ce": 6.23706579208374, "genuineness": 4.406930446624756, "identity": 0.23850546777248383, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c41817851b7888d315a16d940de283f33dddba6a2e3660dac1d90b9573c16b6f.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "c4662be1164cdd0c445c7f276127318fc8b8a5563a5baf49f5b5cd4458c227b6", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e045bc3a84a757de6678ee87c3bd7c57fbb5b6fea332a39f705463ea96e15ed1", "generation_seconds_batch": 23.631710937945172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.90524822473526, "target_z": 1.875, "ce": 6.38003396987915, "genuineness": 4.519899368286133, "identity": 0.4417818486690521, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c4662be1164cdd0c445c7f276127318fc8b8a5563a5baf49f5b5cd4458c227b6.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "c48900186e5df8a98f11d061c51387c21c88eac6d9fa9649b8e47e484e8aeeda", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e845fd8945f4a11f92600a77c0e7df41f2a2d72661f7c407adc2525cd8113ccf", "generation_seconds_batch": 17.69455434405245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23131820559501648, "target_z": 0.26953123613348884, "ce": 6.205295085906982, "genuineness": 4.2249250411987305, "identity": 0.20433752238750458, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c48900186e5df8a98f11d061c51387c21c88eac6d9fa9649b8e47e484e8aeeda.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "92e9868dbc167aa078472d3bd7cf80df0ca748cd014ad7f140494a2d2b6fc867", "generation_seconds_batch": 17.82224960392341, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0501277819275856, "target_z": -0.16210937527733021, "ce": 6.284721851348877, "genuineness": 4.356721878051758, "identity": 0.7819123268127441, "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_Awe/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "c4d64aa8f571b7d6d1e73410ef203a9a882d5f2fbf31e9564e9cebb9374eeeca", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "23d203ae678602f263f0ce2f98f6d75e83975b96d060f8193aa354b628762f2a", "generation_seconds_batch": 22.564539704937488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3985708951950073, "target_z": 0.6679687017445411, "ce": 6.070269584655762, "genuineness": 4.65797233581543, "identity": 0.7088621854782104, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c4d64aa8f571b7d6d1e73410ef203a9a882d5f2fbf31e9564e9cebb9374eeeca.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "c4f7e8e2476434fcd8b2c9e827e3b5f122a91139ab907fa804e130565682f247", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2e681eb45a72907e58c4c9190416b0d3bd0fc9f33bbbbb72581e0f713648b6c3", "generation_seconds_batch": 25.16346226306632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2161506861448288, "target_z": 0.23339843597468377, "ce": 6.252951145172119, "genuineness": 4.432034492492676, "identity": 0.6063631176948547, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c4f7e8e2476434fcd8b2c9e827e3b5f122a91139ab907fa804e130565682f247.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "c57948cea074d284f803dbc4e3de0fb8aadbdc07f9fa07120f918ccedbae1863", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "27dc7eb4b5a5e15375e7553e91bac0874a80a3dca2402752f016f57929689ee9", "generation_seconds_batch": 24.942765551968478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20385268330574036, "target_z": 0.20410153740161477, "ce": 6.356205940246582, "genuineness": 4.7458367347717285, "identity": 0.5926393866539001, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c57948cea074d284f803dbc4e3de0fb8aadbdc07f9fa07120f918ccedbae1863.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "c5c94dcf8c55a97411fdc98134a271cd7502d465f99a039c71f1f90aba10987c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1961e1a6ff7f8708fe1d2200d3ff7cb78664219dcb74bbc244bcc9992e2fd486", "generation_seconds_batch": 15.402962386026047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3108452260494232, "target_z": 0.4589843597468377, "ce": 6.221180438995361, "genuineness": 4.65797233581543, "identity": 0.8218388557434082, "hypothesis": "J'ai trouvé la 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_Awe/c5c94dcf8c55a97411fdc98134a271cd7502d465f99a039c71f1f90aba10987c.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "c5ea351a9512373758c2752c852720a32ba52fc83b0f7bf7d5cd8cf141c13eab", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5c2eeb6e8d029e483456fb55d375772a85e095504d15cdafeb2ba2f8d697e690", "generation_seconds_batch": 23.971369027043693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17720703780651093, "target_z": 0.14062498890679107, "ce": 6.23706579208374, "genuineness": 4.482243061065674, "identity": 0.5222170352935791, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c5ea351a9512373758c2752c852720a32ba52fc83b0f7bf7d5cd8cf141c13eab.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "c6604aed3dd5517d096903e02617c6b834b2d5933926705bc84126a8086b1200", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b69ef9ff7f26b7dfe7b84749127da45f5c0f4ba915c23a485890e074fc93fbfc", "generation_seconds_batch": 26.395248327986337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2528715133666992, "target_z": 2.703125051028761, "ce": 6.292664527893066, "genuineness": 4.758388519287109, "identity": 0.572292685508728, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c6604aed3dd5517d096903e02617c6b834b2d5933926705bc84126a8086b1200.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "c691a3c257594ffa886498b24c8c340d3254d5f4863ea57c6a4aab41414a27fc", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "f7780125de4628b86cd07adcebfdc3c9acd22af8e0c188ec66bd081efb38be61", "generation_seconds_batch": 23.916014860966243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3381376266479492, "target_z": 2.9062501198066566, "ce": 6.205295085906982, "genuineness": 4.6956281661987305, "identity": 0.5413225889205933, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/c691a3c257594ffa886498b24c8c340d3254d5f4863ea57c6a4aab41414a27fc.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "c750dcbc817365d0b221b7898ac518afc588e3340ea88b816c90caf230d51a7c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1963c4ab3fd5f6aa8e61b8ad4fb9e5b2c20c6ec02ae3d0593c31a13c6ac38b32", "generation_seconds_batch": 24.903886437998153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1472819298505783, "target_z": 0.06933594595857182, "ce": 6.213237762451172, "genuineness": 4.055472373962402, "identity": 0.3069058954715729, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c750dcbc817365d0b221b7898ac518afc588e3340ea88b816c90caf230d51a7c.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "c7708a3cb3feaf98ccfb6c92826f6af0f7c6c13dcbf6494dade0acc633deb577", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "deef90d0dff6e200df7c41959e8ef392df656e31ecae616743acd93202d6a01a", "generation_seconds_batch": 22.725501523935236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3329816162586212, "target_z": 0.5117187416800933, "ce": 6.23706579208374, "genuineness": 4.607763767242432, "identity": 0.5263077616691589, "hypothesis": "Die Tür 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_Awe/c7708a3cb3feaf98ccfb6c92826f6af0f7c6c13dcbf6494dade0acc633deb577.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "c772063657722c805d315242792030fa36ea787875970b4d9f5a50c1801135fc", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "07ec0d2448d8a5e2930f433a5c06a3a98c5d7865fefc3ace5cd1f233ca4bd577", "generation_seconds_batch": 24.058495840989053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08456216752529144, "target_z": -0.08007811252013994, "ce": 6.340320587158203, "genuineness": 4.758388519287109, "identity": 0.3006129860877991, "hypothesis": "Die Tür 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_Awe/c772063657722c805d315242792030fa36ea787875970b4d9f5a50c1801135fc.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "c7772e679cee0e97ceff70e03436622e00cda3ebb3d5e454b3cc179d573b7685", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8e7c03d84a86a2480d08527bb02e315f6d94a39ea9fc926e659935bc0d28ad7b", "generation_seconds_batch": 21.801287107984535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.217034101486206, "target_z": 4.999999911254329, "ce": 5.681078910827637, "genuineness": 4.250029563903809, "identity": 0.568978488445282, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c7772e679cee0e97ceff70e03436622e00cda3ebb3d5e454b3cc179d573b7685.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "c7ae119376bd1a04c05c61b6926b33a292c20fb7a2e4119e1858cd4080b174a0", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e884839f5b51ece38a5e0743cd3ebecdf4cf441af380b94bf6545fe84de6f517", "generation_seconds_batch": 24.749223783030175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6004947423934937, "target_z": 3.531249960064448, "ce": 6.062326908111572, "genuineness": 4.7332844734191895, "identity": 0.3737839460372925, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c7ae119376bd1a04c05c61b6926b33a292c20fb7a2e4119e1858cd4080b174a0.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "c7bdbc5b56c3c83d313938324785ccb1aadcde917392ca7c7c3e3a45772b8d17", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9dc4e8f17a4a8d35b8aceb514e96db526f94d68f279567f3f64faf4c99fe01bf", "generation_seconds_batch": 22.245586121920496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4674396812915802, "target_z": 0.8320312627571903, "ce": 6.181467056274414, "genuineness": 4.570107460021973, "identity": 0.6469573974609375, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c7bdbc5b56c3c83d313938324785ccb1aadcde917392ca7c7c3e3a45772b8d17.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "c81aee48b1b335d7906ebdcb1f0e9fa0073db2b98467167861d430311645e2df", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1adf025efb6085d0cf1fb6242371e95ca720c2f0447c83bc27eb3610d4b0b354", "generation_seconds_batch": 24.58926977100782, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7185555696487427, "target_z": 3.8125001863659103, "ce": 6.229123115539551, "genuineness": 4.507347106933594, "identity": 0.4775393009185791, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c81aee48b1b335d7906ebdcb1f0e9fa0073db2b98467167861d430311645e2df.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "b50f31e83a030ac01d18d46a5bf4a49e2ad49af071ac8c8e362558f653e4c3f7", "generation_seconds_batch": 17.305806210031733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07759329676628113, "target_z": -0.09667969429459047, "ce": 6.173524379730225, "genuineness": 4.344170093536377, "identity": 0.6808295249938965, "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_Awe/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "c84be8ffe8042d781318ed1f575ad0876dd4cb692fc70cc8915813b487eff20d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0479c438ad7ca53801ee745ec8f82cdc9e9c4192e0474612b249b87637315831", "generation_seconds_batch": 16.81614069303032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4037269353866577, "target_z": 3.0625001508676415, "ce": 6.197352409362793, "genuineness": 4.68307638168335, "identity": 0.6214535236358643, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c84be8ffe8042d781318ed1f575ad0876dd4cb692fc70cc8915813b487eff20d.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "224700b84394d519a95f51a284a7e257510d668332648168c8d61231e9ee0642", "generation_seconds_batch": 17.417981898994185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5773017406463623, "target_z": 1.0937499866881493, "ce": 6.4912309646606445, "genuineness": 4.425758361816406, "identity": 0.32390737533569336, "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_Awe/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "c89696ac379cab328b14748fa419aeb0889dfab5380cf440d24e53e0c8b1fe09", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8e63dceec798916d2c7dd1a7506c45cb68f3618180fa69df2819e3b0e8bc7cae", "generation_seconds_batch": 24.86532627500128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.361330509185791, "target_z": 5.343749809196806, "ce": 5.903473377227783, "genuineness": 4.174716949462891, "identity": 0.34055447578430176, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c89696ac379cab328b14748fa419aeb0889dfab5380cf440d24e53e0c8b1fe09.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "c8a92038a67d077a4d9cdca44c80deb2251b654429d5b1802578dc053b4ee4f7", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "42183dbd1551f6e71b432fb2406be4592b36627c21cca7b831ab6351072565fe", "generation_seconds_batch": 25.266896513989195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05668671056628227, "target_z": -0.146484377495972, "ce": 5.967014789581299, "genuineness": 4.13078498840332, "identity": 0.6939697861671448, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c8a92038a67d077a4d9cdca44c80deb2251b654429d5b1802578dc053b4ee4f7.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "c8c758d91829313b132aaf61ce8973a648fbb190fb2a7e41b419a8ff6b120054", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f157cfe46673ad0352e60bb2cd03b6b8fa9feb28fa01ae7fdb6b4d4b5be063da", "generation_seconds_batch": 22.629602925037034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3788941204547882, "target_z": 0.621093735024168, "ce": 6.1894097328186035, "genuineness": 4.086852550506592, "identity": 0.4604082703590393, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c8c758d91829313b132aaf61ce8973a648fbb190fb2a7e41b419a8ff6b120054.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "c9b38e0aa640ee4f4d3ea1f9bd140b2151bc554bc7dde242c1e308c7b29c7f0c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "df2749972555a77f94017a6ea5e478d9809fe9ae91f13d3f3d6e734e23453f0b", "generation_seconds_batch": 21.916048810933717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05668671056628227, "target_z": -0.146484377495972, "ce": 6.149696350097656, "genuineness": 4.231201171875, "identity": 0.7798413038253784, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/c9b38e0aa640ee4f4d3ea1f9bd140b2151bc554bc7dde242c1e308c7b29c7f0c.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": "ca1fa9387374a22b14529c284751eaadd1f456edc06063c1e99facc0722f4edc", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9a6049153119e89776c015423a0889af80890f22b6f711188f7a89ee67571bf1", "generation_seconds_batch": 15.539111061953008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9773964881896973, "target_z": 2.0468750909643134, "ce": 5.816103935241699, "genuineness": 4.356721878051758, "identity": 0.35696977376937866, "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_Awe/ca1fa9387374a22b14529c284751eaadd1f456edc06063c1e99facc0722f4edc.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "ca3a810dad5297a6950237226ff72ac15eab1c998b407a5969c893c6a93b9bc3", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "78f753febd91918e0e89de7b19cc0fc0dd7d2fd4c88b8917f062140da0cd5b0a", "generation_seconds_batch": 17.446112751029432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.947881281375885, "target_z": 1.9765625343889477, "ce": 6.395919322967529, "genuineness": 4.457139015197754, "identity": 0.4820014238357544, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ca3a810dad5297a6950237226ff72ac15eab1c998b407a5969c893c6a93b9bc3.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "caaf0bc4a1806500c39945bea78eafb572eccc448a251821a5497a2d432b0072", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "22a1793408b242d4cd48b2e260354a4223b7aa79a57e231e4a2a07a7cdbe04c8", "generation_seconds_batch": 17.069245294085704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7150393128395081, "target_z": 1.4218751087134476, "ce": 6.165581703186035, "genuineness": 4.545003414154053, "identity": 0.735278308391571, "hypothesis": "J'ai trouvé la 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_Awe/caaf0bc4a1806500c39945bea78eafb572eccc448a251821a5497a2d432b0072.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "cb786fe9278e58acbfbd29f8f4503dde5e3179eef4da26c41e8253e4ac381df9", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1ba4a81d047d2ada6821e33955fd2bb75df4d7454e6ec039fd8f50be14080e77", "generation_seconds_batch": 22.67648267291952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1813063770532608, "target_z": 0.15039063359723692, "ce": 6.395919322967529, "genuineness": 4.356721878051758, "identity": 0.47122305631637573, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/cb786fe9278e58acbfbd29f8f4503dde5e3179eef4da26c41e8253e4ac381df9.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "cb7f32f7d967dfd72d173f3e5dc868c805d606ad8e5abcdb5b550c630a9542c8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "ea05b687cf7fcc397bd015c789deb8f6aa2bf8dcb95abfa4a1891214616cb867", "generation_seconds_batch": 24.231034388998523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1479285955429077, "target_z": 2.4531249445339554, "ce": 5.855817794799805, "genuineness": 4.469690799713135, "identity": 0.36849403381347656, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/cb7f32f7d967dfd72d173f3e5dc868c805d606ad8e5abcdb5b550c630a9542c8.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "cbef25b0d1f6b823e8ee3974a02aa5525cf4b617b4741e19accc999d4576f5c3", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "dcdb9f316dd3d115f03ebe8b511fcb5dee8b2b14365c0ce67d73b8e42bcb596c", "generation_seconds_batch": 17.054319567978382, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6658473014831543, "target_z": 1.3046875144211716, "ce": 6.197352409362793, "genuineness": 4.758388519287109, "identity": 0.5584681034088135, "hypothesis": "Die Tür 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_Awe/cbef25b0d1f6b823e8ee3974a02aa5525cf4b617b4741e19accc999d4576f5c3.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "cca6babd9612279b44ac486c1e14e083f3a5d1ead8d68f925696b4f969962539", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "194f22b68798d14cf232c217e94c9a38f22db7945c124ef006d94843348a7bf8", "generation_seconds_batch": 20.701695474097505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5773017406463623, "target_z": 1.0937499866881493, "ce": 6.173524379730225, "genuineness": 4.796044826507568, "identity": 0.8216779232025146, "hypothesis": "J'ai trouvé la 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_Awe/cca6babd9612279b44ac486c1e14e083f3a5d1ead8d68f925696b4f969962539.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": "cdaf5b8e730275dbad1901ae6aaad574a41f8c94cae0eb16d388f399ceaba0a0", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Someone moved the little blue chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6a8161a89eed5797b19ad5bba3f64d7d5a1fdd4e2dbb9bbf5743768fc21a2c3c", "generation_seconds_batch": 17.519703989033587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3774912357330322, "target_z": 3.0000001952404776, "ce": 6.38003396987915, "genuineness": 4.432034492492676, "identity": 0.3523801565170288, "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_Awe/cdaf5b8e730275dbad1901ae6aaad574a41f8c94cae0eb16d388f399ceaba0a0.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "cdc17e92cf4a736ee96537f14a7075d28eda43bb2582c7b8db31d8500349927b", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "625e941cfc0ad4a73f1427ada905a587c966921b3a5871854c51b91881097acd", "generation_seconds_batch": 18.215019547962584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.051767513155937195, "target_z": -0.15820312805063247, "ce": 6.1894097328186035, "genuineness": 4.494794845581055, "identity": 0.5190659165382385, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/cdc17e92cf4a736ee96537f14a7075d28eda43bb2582c7b8db31d8500349927b.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "ce2d7491a76c4fa762580ecbeba2d2bdb25f571334adc7ee687f284ac4f54bf2", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4ba118ab4919af2be3db1d44b65617a71f2daba806ba1102c83930ba73676ba0", "generation_seconds_batch": 19.34842471103184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4510423541069031, "target_z": 0.792968754991944, "ce": 6.157639026641846, "genuineness": 4.532451152801514, "identity": 0.7243978977203369, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ce2d7491a76c4fa762580ecbeba2d2bdb25f571334adc7ee687f284ac4f54bf2.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "ce371566aed041c7b4b9852e61188a4c228265620d0b3f515ee38e835646ee90", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "845c6cf98b84b69768f9d3724af2bc318b6a8bd115f49f0030fab746ce90b7ac", "generation_seconds_batch": 27.06583886197768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1821262389421463, "target_z": 0.15234374833601866, "ce": 6.125868320465088, "genuineness": 4.545003414154053, "identity": 0.37975049018859863, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ce371566aed041c7b4b9852e61188a4c228265620d0b3f515ee38e835646ee90.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "ce55a5cf95dcd0c94d9659f3ab907bec25cd2eee5897e4132135f4ffa7a30ce6", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f829bca23e5ba9bc0a5d823ad65c2050031929a8d3e3ac37673db9dd1c6f941b", "generation_seconds_batch": 24.584344813018106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7972626686096191, "target_z": 4.000000053247403, "ce": 6.324435234069824, "genuineness": 4.68307638168335, "identity": 0.5374924540519714, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ce55a5cf95dcd0c94d9659f3ab907bec25cd2eee5897e4132135f4ffa7a30ce6.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": "ce5d9b543f276b020a776e6138755d698668a8d75e15042afae7974001188624", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Your message arrived after I had left.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a3ed52300737a45ff9d738b2c8b339c6a25b4b88c65c9e4b49f7b9d56b362bab", "generation_seconds_batch": 23.786815706058405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26165327429771423, "target_z": 0.34179690744763613, "ce": 6.252951145172119, "genuineness": 4.425758361816406, "identity": 0.43631741404533386, "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_Awe/ce5d9b543f276b020a776e6138755d698668a8d75e15042afae7974001188624.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "ceac1bbfe8fbf2779f64c1b91494eb4acca90bd0438cc4ac5025fce622506212", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "797da2e79085e49a84682fced2e2c8120644280575c4c6d0e78597d5beb67791", "generation_seconds_batch": 21.922971515916288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.230152130126953, "target_z": 5.031250315047134, "ce": 5.847874641418457, "genuineness": 4.369274139404297, "identity": 0.531867265701294, "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_Awe/ceac1bbfe8fbf2779f64c1b91494eb4acca90bd0438cc4ac5025fce622506212.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "cf5ffa098edd4fe6fade7c92eb488a554b5b1b5aeddd06fcf01112f78fba4d9b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8d3d3c0b043bf0b8e6e207f4c175c5d53ad7b1161f7dfbe9b355795583195def", "generation_seconds_batch": 22.781671465956606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0561035871505737, "target_z": 2.234374957845806, "ce": 5.998785495758057, "genuineness": 4.469690799713135, "identity": 0.556378960609436, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/cf5ffa098edd4fe6fade7c92eb488a554b5b1b5aeddd06fcf01112f78fba4d9b.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "aedb8e46084a64378826581e2dccb67b37658d181d1b97173279b253a3570ee5", "generation_seconds_batch": 18.17946313205175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34118029475212097, "target_z": 0.531250031060985, "ce": 6.475345611572266, "genuineness": 4.582659721374512, "identity": 0.5643196105957031, "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_Awe/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "cfa493f355187bc0d46f36c3b5862b087d3d418de091b4fa2f2c2b139eb1d4c9", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "77cdfd40ec450bb696089d28454f466ec468934458817ae3c296bf80334d7723", "generation_seconds_batch": 22.240110952057876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1854057013988495, "target_z": 0.16015624278941418, "ce": 6.324435234069824, "genuineness": 4.21237325668335, "identity": 0.226558119058609, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/cfa493f355187bc0d46f36c3b5862b087d3d418de091b4fa2f2c2b139eb1d4c9.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": "cfac28967061f78bf93a04ed9373ceddee13b752bb2c88995af6b92c06f9befa", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "212f4da0b1daf29099dafa93ba62d8ad986dfdc8a1a725fed02bf4252b4c3c2d", "generation_seconds_batch": 17.27704958897084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2263990044593811, "target_z": 0.2578124767042612, "ce": 5.780362129211426, "genuineness": 4.545003414154053, "identity": 0.6323939561843872, "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": 0.120000000000001, "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_Awe/cfac28967061f78bf93a04ed9373ceddee13b752bb2c88995af6b92c06f9befa.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": "cfb39f9650421ee80e337f2ef8f13415d1ce0706132f58801b7708c529c21669", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "acf6b9d4dfa4b29b6569cddf3bce83430aa24b37aff43c87fe35d964efaedb8f", "generation_seconds_batch": 17.432622501975857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9183661341667175, "target_z": 1.9062501198066566, "ce": 5.752562999725342, "genuineness": 4.2374773025512695, "identity": 0.35782110691070557, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/cfb39f9650421ee80e337f2ef8f13415d1ce0706132f58801b7708c529c21669.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": "d09ea6f69c6ce0a505e28c4d3e2eb54b3186a944aaf24e2ed449eff5d9e6da90", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8e2eccfd434d8ab2ba9211c04509f4f6ac715415b9156e216ee7f15c161de706", "generation_seconds_batch": 17.27049375406932, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5035138130187988, "target_z": 0.9179688082393469, "ce": 5.621508598327637, "genuineness": 4.243753433227539, "identity": 0.7483538389205933, "hypothesis": "Les collés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/d09ea6f69c6ce0a505e28c4d3e2eb54b3186a944aaf24e2ed449eff5d9e6da90.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": "d0fe33c55a486e7aef889f7e58431bffd3fafc2040da24dba97389322803e534", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The road turns left behind the bridge.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "da87ae899c22b89044ce00e9cedc2dbc73d67b9c1a7a46bd6b792b87a1f0147c", "generation_seconds_batch": 16.697118956013583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.590419590473175, "target_z": 1.1249999645017315, "ce": 6.356205940246582, "genuineness": 4.432034492492676, "identity": 0.43731406331062317, "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_Awe/d0fe33c55a486e7aef889f7e58431bffd3fafc2040da24dba97389322803e534.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "42fc5ad658226ceee7c33f643e1cefa399d1cec78fced3fdd2679af5497ae9d7", "generation_seconds_batch": 20.280573131050915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10382901877164841, "target_z": -0.03417968542002332, "ce": 6.419747352600098, "genuineness": 3.998987913131714, "identity": 0.4031819701194763, "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_Awe/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "d1612534a015da24649156244dca106d3392dee540a098721dd9b1c9be83b2be", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a53d333c4ad9ced4b488e2170e3594162411fbea7ca7395a8c901829516e8858", "generation_seconds_batch": 17.03526578610763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0495446920394897, "target_z": 2.218750039935552, "ce": 6.229123115539551, "genuineness": 4.821148872375488, "identity": 0.677838146686554, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/d1612534a015da24649156244dca106d3392dee540a098721dd9b1c9be83b2be.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "d1b3e92a7ece3bfacbde29b8ddce098375bf339acf2862ea459e576d99dd3b25", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "99011156f88a1781bf043d881bc1dff8b0297dfe43e38f6a53958e1e04ec5fc2", "generation_seconds_batch": 23.64946450095158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3559378683567047, "target_z": 0.5664062383521307, "ce": 6.372091293334961, "genuineness": 4.18099308013916, "identity": 0.5489410758018494, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/d1b3e92a7ece3bfacbde29b8ddce098375bf339acf2862ea459e576d99dd3b25.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "d1c239fe9454e6cc802f1fe62424723e95e441d1cecfeb773d62fdc04c6abcbe", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1ba15b40fb4e46a72e3961259e22ff5334005476bb6afa44ec2660b2a8da1e45", "generation_seconds_batch": 23.06170879898127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14195279777050018, "target_z": 0.056640629159953354, "ce": 6.109982967376709, "genuineness": 4.268857479095459, "identity": 0.4718169569969177, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/d1c239fe9454e6cc802f1fe62424723e95e441d1cecfeb773d62fdc04c6abcbe.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "d1c7ae0853f04f3ed7544a8ddaad11b47f48ae97c81330f88a06a3bd277bcffa", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8d7cc6c90dc52a3ae326e46cf0d0365599ebb7f336cf3ed9fefdee908c8da055", "generation_seconds_batch": 23.52375392697286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1915546953678131, "target_z": 0.17480467432681437, "ce": 6.141753673553467, "genuineness": 4.394378662109375, "identity": 0.32015472650527954, "hypothesis": "La puerta sigue abierta. ¿He dejado tu abrigo sobre la silla? Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/d1c7ae0853f04f3ed7544a8ddaad11b47f48ae97c81330f88a06a3bd277bcffa.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "d20a728510a35bc3fac70bb6c17c9e86f88a268afa5f8adca4d90cb4d1d72fcf", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d35fe49972b8593b22f1f873ce865bca7a8cac95b2cb46f6fd0222401d11f51c", "generation_seconds_batch": 24.703545121941715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30592602491378784, "target_z": 0.4472656003176101, "ce": 6.2767791748046875, "genuineness": 3.9550557136535645, "identity": 0.18839135766029358, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/d20a728510a35bc3fac70bb6c17c9e86f88a268afa5f8adca4d90cb4d1d72fcf.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "d22e7a99d4fd7a3eeb36de6c6e4b2ec5243cccc6cd080865e4af05bb68bc0880", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d23b1ca7002aff59af3b88e8c0a877f5218ab91576e772932aa92d90a736c265", "generation_seconds_batch": 24.091228040051647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3053429126739502, "target_z": 2.8281249622830895, "ce": 5.530168056488037, "genuineness": 4.381826400756836, "identity": 0.2707153260707855, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/d22e7a99d4fd7a3eeb36de6c6e4b2ec5243cccc6cd080865e4af05bb68bc0880.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "5b56935ef80a173cf9136689b0da31adc4f87da3623fd0bf157fc2ed8eed892f", "generation_seconds_batch": 17.81157343601808, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5117124319076538, "target_z": 0.9374999556271643, "ce": 6.340320587158203, "genuineness": 4.293961524963379, "identity": 0.5645180940628052, "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_Awe/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "d3481df67b079f59c0fcb9a0d5d8cf926f8be85f03cd0d05e65e5022c58f09ef", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3fa828c5a39b671c3236322ff0f80549c213996c626ba199367a476e1548fa1f", "generation_seconds_batch": 20.701695474097505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0561035871505737, "target_z": 2.234374957845806, "ce": 6.197352409362793, "genuineness": 4.482243061065674, "identity": 0.7194440960884094, "hypothesis": "J'ai trouvé la 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_Awe/d3481df67b079f59c0fcb9a0d5d8cf926f8be85f03cd0d05e65e5022c58f09ef.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": "d3494cfa63a293303e7e688a810ada902bf63917ea765e639ed3d5a2e47f8ec5", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b422ef52d197a76a114ad5a04e2a2290deedbadd10c714cba30ee9092aeff9c3", "generation_seconds_batch": 24.040325321024284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12350580841302872, "target_z": 0.012695316798618465, "ce": 6.09409761428833, "genuineness": 4.3127899169921875, "identity": 0.35986217856407166, "hypothesis": "Je bericht konde dat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "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_Awe/d3494cfa63a293303e7e688a810ada902bf63917ea765e639ed3d5a2e47f8ec5.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "d3b1e0a75f1c0c886df653fc82e964d03d6537524d78e8db8b8887ef4f9777da", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "03c721f75accff025220f1744c5cac6eaf7d1fdbd39d92d8cea1378eec29b4db", "generation_seconds_batch": 17.468123214086518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.675685703754425, "target_z": 1.3281250332796268, "ce": 6.149696350097656, "genuineness": 4.582659721374512, "identity": 0.7791266441345215, "hypothesis": "j'ai trouvé la 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_Awe/d3b1e0a75f1c0c886df653fc82e964d03d6537524d78e8db8b8887ef4f9777da.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "ba365b1338dfa77688683fad57fa91cce835a0bc9af2ea6183e1eb396e37edf3", "generation_seconds_batch": 17.291537005919963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10341908782720566, "target_z": -0.03515624278941419, "ce": 6.1020402908325195, "genuineness": 4.419482707977295, "identity": 0.6711248159408569, "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_Awe/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "d442db342d3e3ab0caeaa33d373164e70a1223a684703f1134da7d2376d870a9", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "bf61a553889176395fd1f318b2f738e96210320ba646defe9e11a278bb78aba8", "generation_seconds_batch": 24.715256360010244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43628475069999695, "target_z": 0.7578124767042612, "ce": 6.205295085906982, "genuineness": 4.149612903594971, "identity": 0.174756720662117, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/d442db342d3e3ab0caeaa33d373164e70a1223a684703f1134da7d2376d870a9.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "d520f9b8f2734212d1707de56cdb597cf57da495a92bd5dbd64e2a6488e015aa", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "300ebf63128d7c6a842bde85d33a527843f3abe599f3e5bd56bb7b69f3d739a2", "generation_seconds_batch": 21.758353341021575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.980912685394287, "target_z": 4.4375000266237015, "ce": 5.935244083404541, "genuineness": 4.570107460021973, "identity": 0.3534088730812073, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/d520f9b8f2734212d1707de56cdb597cf57da495a92bd5dbd64e2a6488e015aa.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "d5865d5f86c5b159b73666dd80dc59b78db656bbf5239f6c21aebbf706845184", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "608f66fd511f842bb48798ee49a582b2b5a4f47181649553051e83745aa8796c", "generation_seconds_batch": 17.234794431948103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7185555696487427, "target_z": 3.8125001863659103, "ce": 6.292664527893066, "genuineness": 4.582659721374512, "identity": 0.5471879243850708, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/d5865d5f86c5b159b73666dd80dc59b78db656bbf5239f6c21aebbf706845184.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "d5ffcd66b869426aa7ca886b6ff479b7a2990f1c62015a4aae8522b1a4f9f781", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "95150f4c8cbdf6d8f4f122e219077b657beb6134a506c9ff26bc3faa8bc7cd4c", "generation_seconds_batch": 21.885285104974173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5641838908195496, "target_z": 1.062500008874567, "ce": 6.117925643920898, "genuineness": 4.20609712600708, "identity": 0.3551757037639618, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/d5ffcd66b869426aa7ca886b6ff479b7a2990f1c62015a4aae8522b1a4f9f781.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "d664f27a68b344bbd65b9e6def9b005baa9347e7e67ee65ba82e9a923ab8a7e8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4e703f215ab98a47c8ddd9b78f1572dbba2e784324ac348586ddfb39cc435e22", "generation_seconds_batch": 26.927808119915426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1020160913467407, "target_z": 2.3437499511898805, "ce": 5.839932441711426, "genuineness": 4.432034492492676, "identity": 0.4764648973941803, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/d664f27a68b344bbd65b9e6def9b005baa9347e7e67ee65ba82e9a923ab8a7e8.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "d6d4ef1240814b590ca94e42a7c2334270a9d23c4d57ddfa75fe064e8cd461f8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fe15803868b7c014f3daa3f7aa655f2cbb82eff7cc15f3c417becda2b308a6e2", "generation_seconds_batch": 25.128766463021748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47727805376052856, "target_z": 0.8554687106191082, "ce": 6.078212261199951, "genuineness": 4.469690799713135, "identity": 0.3428647518157959, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/d6d4ef1240814b590ca94e42a7c2334270a9d23c4d57ddfa75fe064e8cd461f8.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "d7127abc7efdd1efb852aeb5dfc378e32872cde2fc4678a7c14bde19e06bd486", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "660d19b78fde6cd44c2c429fd787463e2e5e2292aa9c88e70c26bc5ba383e66a", "generation_seconds_batch": 22.094267684966326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7710269689559937, "target_z": 3.9375000976202386, "ce": 6.3641486167907715, "genuineness": 4.68307638168335, "identity": 0.40613430738449097, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/d7127abc7efdd1efb852aeb5dfc378e32872cde2fc4678a7c14bde19e06bd486.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "d7d8c92382e6ae716269636bd9f23a6932e8a5964d5155d8a9a0c6caaf89c01f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b2600f98710cb162e389dade2afe6c069f993fafb88ceb52cb20ae4ed186a8e2", "generation_seconds_batch": 25.718000852968544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7281571626663208, "target_z": 1.4531250865270298, "ce": 6.268836498260498, "genuineness": 4.306513786315918, "identity": 0.3442733585834503, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/d7d8c92382e6ae716269636bd9f23a6932e8a5964d5155d8a9a0c6caaf89c01f.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "d80198b650606ff67814d2b9cf2870f521e30824ee027c94f962ffd404ddbef8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "2ec2276acde1d82a327c48d41d19698e6541ec98dfe866aa5ab159a6c4e212dc", "generation_seconds_batch": 23.999984991038218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2200769186019897, "target_z": 2.625000177491343, "ce": 6.221180438995361, "genuineness": 4.7081804275512695, "identity": 0.543533205986023, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/d80198b650606ff67814d2b9cf2870f521e30824ee027c94f962ffd404ddbef8.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "d80d55dd18775d3f63ddf9f1c2c02fbde56b5d2da0e3b7a5698e860d0c98bc4a", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b80aff922403ce3039c2673a95e3b6991cf819bfd7e0f15ebd766769da698278", "generation_seconds_batch": 23.604537803097628, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07185423374176025, "target_z": -0.1103515684625998, "ce": 6.221180438995361, "genuineness": 4.507347106933594, "identity": 0.6850008964538574, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/d80d55dd18775d3f63ddf9f1c2c02fbde56b5d2da0e3b7a5698e860d0c98bc4a.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": "d817ee6054ea1cf0eea9a08c90e3a73558121eefdb0603574adf84ca51634931", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7001e95ffbe1cd21b082af34587f64440bbd27a629311157501865d101f08ae9", "generation_seconds_batch": 17.20223418995738, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.99051433801651, "target_z": 2.0781250687778954, "ce": 6.157639026641846, "genuineness": 4.595211505889893, "identity": 0.21633100509643555, "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_Awe/d817ee6054ea1cf0eea9a08c90e3a73558121eefdb0603574adf84ca51634931.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": "d823ac8c75ecf0c9046c8c9b9b34dbfe7d54341fcaf584c0b4d506da13ae099f", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2f851b72bc132fcf23902a63ecd4a90808c3a282cf72660eae8a21fbbe0c9861", "generation_seconds_batch": 17.19543138402514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07431383430957794, "target_z": -0.104492188747986, "ce": 6.09409761428833, "genuineness": 4.557555198669434, "identity": 0.11558225750923157, "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_Awe/d823ac8c75ecf0c9046c8c9b9b34dbfe7d54341fcaf584c0b4d506da13ae099f.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "d86c432179b96e5245c321d7aac30852e337e1351ec3658045a23297b7b98cc7", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "32e9c3e083f67229f2e2fca578130e5fc6234a658b2a6840eaf9c25f4c5f8bf6", "generation_seconds_batch": 23.555408046930097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11325748264789581, "target_z": -0.011718741680093295, "ce": 6.181467056274414, "genuineness": 4.758388519287109, "identity": 0.7271456718444824, "hypothesis": "La porte est encore ouverte , j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/d86c432179b96e5245c321d7aac30852e337e1351ec3658045a23297b7b98cc7.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "d8a0083c9b1de01859b349076f70cb199c43596ca3a52b95ba830862f06446bc", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6cc2a94681cac4788a3d30f61dd903ac18c11eaf2843b8bba54fbd02fa2c9b50", "generation_seconds_batch": 23.81005395599641, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07923303544521332, "target_z": -0.09277342931875841, "ce": 6.332377910614014, "genuineness": 4.557555198669434, "identity": 0.535728931427002, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/d8a0083c9b1de01859b349076f70cb199c43596ca3a52b95ba830862f06446bc.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": "d90f50ef45ad33ad200e846d02e5284bc10ca80302ec33269f7efc33a410b12b", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "4dec9ff5d3cb91c68fc5a602ad490cd6c42a77e3cd02dabb73633a3318cb1d41", "generation_seconds_batch": 17.28300430206582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4037269353866577, "target_z": 3.0625001508676415, "ce": 5.7684478759765625, "genuineness": 4.482243061065674, "identity": 0.7228492498397827, "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": 0.120000000000001, "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_Awe/d90f50ef45ad33ad200e846d02e5284bc10ca80302ec33269f7efc33a410b12b.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "d944317f5b4d3d3898d5df78cbc9d6cdf53d0a1d839ad81fc726b61e924d215e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d557d4eb6e50efcac489feb30d76e6ec2babccccc565b6a3d2e5fbaf97527237", "generation_seconds_batch": 22.86908679001499, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3772543966770172, "target_z": 0.6171875055466045, "ce": 6.221180438995361, "genuineness": 4.65797233581543, "identity": 0.24060890078544617, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/d944317f5b4d3d3898d5df78cbc9d6cdf53d0a1d839ad81fc726b61e924d215e.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "d94dd080c2ae80b4ec5db1cc7e64c6ba44753c226299092508eddb2c2f4e0d8f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "379c75d9cf426ddfc373fb964947b8f2a59446e0a02b7ed1f10bbc8e097ad3ce", "generation_seconds_batch": 23.706010808004066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0036321878433228, "target_z": 2.1093750465914773, "ce": 5.605623245239258, "genuineness": 4.400654315948486, "identity": 0.465940922498703, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/d94dd080c2ae80b4ec5db1cc7e64c6ba44753c226299092508eddb2c2f4e0d8f.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": "d957b5b0afb05e911e6c63c707fc651eb74737b3ecbc07016b8ab0bc361b6b23", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bac6ab9d48b496ce0eebae86182940cab9592c42d0e3c0f0aec4d98ec7c6efbf", "generation_seconds_batch": 15.612214984023012, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13416406512260437, "target_z": 0.03808593264672109, "ce": 6.062326908111572, "genuineness": 4.570107460021973, "identity": 0.8225371241569519, "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_Awe/d957b5b0afb05e911e6c63c707fc651eb74737b3ecbc07016b8ab0bc361b6b23.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "d99989e512d5dceba44944206c60b7258f017168262b478680b63bc87dce7957", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c48ec161188b04d836c2b5718de9d851a9045e50b92ca282e369e31c5b1be1db", "generation_seconds_batch": 21.99291931290645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10218928754329681, "target_z": -0.03808593264672109, "ce": 6.197352409362793, "genuineness": 4.105680465698242, "identity": 0.8220811486244202, "hypothesis": "ik 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_Awe/d99989e512d5dceba44944206c60b7258f017168262b478680b63bc87dce7957.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": "da03d42efba5c4ebefa702e94d15ca108b5345f331d25c3166759327e9d7e3a5", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "16be614fc1a48a0a408b6c109bd874657869051215d58f0a86fd690b48716825", "generation_seconds_batch": 23.393288691993803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.164562702178955, "target_z": 4.875, "ce": 6.038498878479004, "genuineness": 4.3504462242126465, "identity": 0.4305376410484314, "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_Awe/da03d42efba5c4ebefa702e94d15ca108b5345f331d25c3166759327e9d7e3a5.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "dafa4313e29b2f141e730ceb5b6d6e7ff41713fefb95f67cc3f7cc5a9ebff680", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9dd5e1b9cb00d050b626549024a20f484c602fa266cf8e619729568c99a423a1", "generation_seconds_batch": 17.554142318083905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2231195569038391, "target_z": 0.25000001774913433, "ce": 6.221180438995361, "genuineness": 4.507347106933594, "identity": 0.49068009853363037, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het Oude Raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/dafa4313e29b2f141e730ceb5b6d6e7ff41713fefb95f67cc3f7cc5a9ebff680.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "8dcb1402bcc50d01079dc8751a81f1e8c137968e57d0b85efcd70e4c2be6ef5a", "generation_seconds_batch": 20.311453656991944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11694687604904175, "target_z": -0.0029296898573068996, "ce": 6.41180419921875, "genuineness": 4.13078498840332, "identity": 0.4058080315589905, "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_Awe/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.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": "db1e4baf9f4a2eadbab428d93caec0c4c03e5f467243329dea58b41608fad151", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "be3d9d0fc7ff750772f8ca0389b34ab8991091ee3dfde635714c9f5c187b5ed1", "generation_seconds_batch": 17.29291858104989, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2922251224517822, "target_z": 2.7968751264625817, "ce": 5.8875885009765625, "genuineness": 4.632867813110352, "identity": 0.630184531211853, "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": 0.120000000000001, "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_Awe/db1e4baf9f4a2eadbab428d93caec0c4c03e5f467243329dea58b41608fad151.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": "db8e2acc0a99ab2fee10c396f887bee351b26af54947f9fbce7c21f1973331eb", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78316e5d2fb9c04a296acd52a14df48d7166ff32d6b47ab68c2d765ad4fd220b", "generation_seconds_batch": 25.2313629060518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30510616302490234, "target_z": 0.44531248557882835, "ce": 5.780362129211426, "genuineness": 4.469690799713135, "identity": 0.5962581634521484, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rongé mon téléphone. Dis-moi quand nous pourrons parler.", "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_Awe/db8e2acc0a99ab2fee10c396f887bee351b26af54947f9fbce7c21f1973331eb.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "dbc2015c94fc2c431fc84c45b68bef84cb3de0a1c98c0aa41823afb66a3f31f3", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e5fceaf8e95c2e8637d6532e43f65a594580f68559e3d0f7a0c08c51651d82ee", "generation_seconds_batch": 22.39641169901006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2862492501735687, "target_z": 0.4003906335972369, "ce": 5.8875885009765625, "genuineness": 3.8797430992126465, "identity": 0.4570547938346863, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/dbc2015c94fc2c431fc84c45b68bef84cb3de0a1c98c0aa41823afb66a3f31f3.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "dc070882bfdb7709a2c4e2566ba071f1915d81e4782481eb69b0c684b21633a7", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "8eae2f17a8cf147363e9744c01cbab049ca71c51777f87e300c40af68757e60f", "generation_seconds_batch": 24.289364001946524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07431383430957794, "target_z": -0.104492188747986, "ce": 5.8875885009765625, "genuineness": 4.582659721374512, "identity": 0.6245659589767456, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/dc070882bfdb7709a2c4e2566ba071f1915d81e4782481eb69b0c684b21633a7.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "dc4dd37e5c9453b719246e6ae6bdb0afde0773b98068f116a07d33f6064fa22f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f2b51a1045f3a67864f9133535b61565455a7cd89e1ba278902ec47896d0520b", "generation_seconds_batch": 23.94108139409218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8497340679168701, "target_z": 4.124999964501732, "ce": 6.324435234069824, "genuineness": 4.557555198669434, "identity": 0.3084679841995239, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/dc4dd37e5c9453b719246e6ae6bdb0afde0773b98068f116a07d33f6064fa22f.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "dc63f2a3dae55d2b142cbffd62508c84f1a1c2bfc0e2bd99b6fdef5596424b77", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "4fa843eaab272d855b5c2e5c90d1c033360db237fb7fe8848c0ccb8146ad86f4", "generation_seconds_batch": 24.445872443029657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7839080691337585, "target_z": 1.5859375987295596, "ce": 6.427689552307129, "genuineness": 4.557555198669434, "identity": 0.6073909997940063, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/dc63f2a3dae55d2b142cbffd62508c84f1a1c2bfc0e2bd99b6fdef5596424b77.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "dc71b6880d70f45ac0fd853a23b9b7ceec4bb37033b09ca5e9d4cecd243b4b8f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7190ad34728222d6d205fa18187df1f3bd27547f6fdf318ce4f9616d824c820e", "generation_seconds_batch": 24.57433576998301, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.856056272983551, "target_z": 1.7578125477007984, "ce": 6.475345611572266, "genuineness": 4.607763767242432, "identity": 0.622145414352417, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/dc71b6880d70f45ac0fd853a23b9b7ceec4bb37033b09ca5e9d4cecd243b4b8f.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": "dc9ca004ce6c5bc2de3d620a87efea66483716c00d03d50d054b27e958e88e94", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6d47adcbe1065cf75d452ad125be82a9b0cb29329370cb916824cd83181a0b57", "generation_seconds_batch": 17.526757068932056, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7054376602172852, "target_z": 3.7812500665592537, "ce": 5.871703147888184, "genuineness": 4.406930446624756, "identity": 0.43711405992507935, "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_Awe/dc9ca004ce6c5bc2de3d620a87efea66483716c00d03d50d054b27e958e88e94.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "dca00c51e5cdb1ed446bfd58b353f0899838bc4160bf5311f97c4accf1800339", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3b15cc452831b8d28930c4493562c3417dfe106c9fe7fbf7740e0ec38b29cab0", "generation_seconds_batch": 17.288380017038435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10382901877164841, "target_z": -0.03417968542002332, "ce": 6.4515180587768555, "genuineness": 4.7834930419921875, "identity": 0.5673650503158569, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/dca00c51e5cdb1ed446bfd58b353f0899838bc4160bf5311f97c4accf1800339.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "dceb46db1cbf1204c9260c8feeb1e2671e90ed5d2b57080f7ff62c939ba9732e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "0ba1ecf24f8edbeec049048b3c0e1ccc9bf3d93a00ceee2bbfb4ed5f0ab48647", "generation_seconds_batch": 24.85153456008993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5149919390678406, "target_z": 0.9453125565753656, "ce": 6.173524379730225, "genuineness": 4.833701133728027, "identity": 0.4890234172344208, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/dceb46db1cbf1204c9260c8feeb1e2671e90ed5d2b57080f7ff62c939ba9732e.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "dd3f5743446f0e5b52e3d56be85cbe0337ac4a6864f602cba836959f2d6072ba", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a518ebd1f16cc58a6321a0ebf346b1f3e9e984e07d5928a21daa38d466c4da5b", "generation_seconds_batch": 23.936594696016982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32806241512298584, "target_z": 0.49999998225086567, "ce": 6.268836498260498, "genuineness": 4.582659721374512, "identity": 0.5592095851898193, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/dd3f5743446f0e5b52e3d56be85cbe0337ac4a6864f602cba836959f2d6072ba.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "dd447f1dc97488a1e85a5c7e3a394166531dad7cef169fc61a888e06e55d2da9", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "501a9f3e96c943dcfb5157011666a052ffd2208073feaa09e0833705b430fcb9", "generation_seconds_batch": 23.36996362998616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12432567030191422, "target_z": 0.014648431537400195, "ce": 6.157639026641846, "genuineness": 4.7332844734191895, "identity": 0.6830190420150757, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/dd447f1dc97488a1e85a5c7e3a394166531dad7cef169fc61a888e06e55d2da9.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": "de4595760486d1309968d5e7b53ea343213f30725865155d4d95500634bc7ce9", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e5baa605a6aa212a54cf06e1443118ecc0405be802c0be66e7b581455f396d3", "generation_seconds_batch": 25.2313629060518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29936710000038147, "target_z": 0.43164061141081905, "ce": 5.935244083404541, "genuineness": 4.6956281661987305, "identity": 0.699297308921814, "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_Awe/de4595760486d1309968d5e7b53ea343213f30725865155d4d95500634bc7ce9.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "de7bb0ec5692fea1addedf2f5b517c04f3af0476c5e978f9eececd5d0b3b2847", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1e75a21b8f6c529d1f142d7c201412b6fc0a62b7e6e49ef1a77a90c89c83f436", "generation_seconds_batch": 22.995427452027798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6428910493850708, "target_z": 1.2500000177491344, "ce": 5.9431867599487305, "genuineness": 4.262581825256348, "identity": 0.4465453624725342, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/de7bb0ec5692fea1addedf2f5b517c04f3af0476c5e978f9eececd5d0b3b2847.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": "de882dbac69951b59e5460edbecd3c403826957ed57e9fbc46fcf061eda15c87", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The road turns left behind the bridge.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "59287ead3c4719446e9abc36f55947866594e689d95cebe32c0682b0d3e882c5", "generation_seconds_batch": 17.217853924026713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8429384231567383, "target_z": 1.7265625698872162, "ce": 6.24500846862793, "genuineness": 4.375550270080566, "identity": 0.5984650254249573, "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_Awe/de882dbac69951b59e5460edbecd3c403826957ed57e9fbc46fcf061eda15c87.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "de8e93bbb62ee483b85c1eec7b712dba49e7bc38dc4cb10c7655952821f3dd10", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "c74b95414dc81d547e7c0f79d1bd3986f13a2b898afaecace5a826078c092521", "generation_seconds_batch": 26.961197689990513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01979273557662964, "target_z": -0.23437499334407463, "ce": 6.316492557525635, "genuineness": 4.519899368286133, "identity": 0.6209083199501038, "hypothesis": "Die Tür 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_Awe/de8e93bbb62ee483b85c1eec7b712dba49e7bc38dc4cb10c7655952821f3dd10.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "deeaa32054fa6646bc9e7b1e2c7a67596f7b27ce97bba7bef752499d165b11ed", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "efb30b89a40d01b4d892c66a7913ee8f1706bf959f18b05ca90d6873b77e9fb7", "generation_seconds_batch": 19.376216926961206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.282623529434204, "target_z": 5.156250226301462, "ce": 6.332377910614014, "genuineness": 4.507347106933594, "identity": 0.42701205611228943, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/deeaa32054fa6646bc9e7b1e2c7a67596f7b27ce97bba7bef752499d165b11ed.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "def9a249db3d2c8662719e409a0785d39e844a59151f107e34458286c5c2673c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "386fac929d7bbb8713008adf86ddee4158398040e5b8421c3e24ebaf3489ee0d", "generation_seconds_batch": 23.872623622999527, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.140313059091568, "target_z": 0.052734364184121287, "ce": 6.260893821716309, "genuineness": 4.375550270080566, "identity": 0.7504352331161499, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/def9a249db3d2c8662719e409a0785d39e844a59151f107e34458286c5c2673c.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": "dfaaba5c4f48765362b4086b164ba88bb8483ae238ae489602ce20db062d8c4f", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f29531e526f237999958ea5e4cd898b318793b9b01eeebc4217a68df2a362dc0", "generation_seconds_batch": 18.215264296974055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.760951817035675, "target_z": 1.5312501020575222, "ce": 6.221180438995361, "genuineness": 4.557555198669434, "identity": 0.4552338123321533, "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_Awe/dfaaba5c4f48765362b4086b164ba88bb8483ae238ae489602ce20db062d8c4f.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "e0e9d843ec6c29ee23d48935af7a77698aa4a97c88f1b7c02150e24642a57328", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4a9790eb43ceb8cb175a8a783981a0679c05630dbce0efd7797c6f54eb9f1ba8", "generation_seconds_batch": 23.907403483986855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23623740673065186, "target_z": 0.2812499955627164, "ce": 6.173524379730225, "genuineness": 4.432034492492676, "identity": 0.49077919125556946, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e0e9d843ec6c29ee23d48935af7a77698aa4a97c88f1b7c02150e24642a57328.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "e1546adc3110865952f05b6584de483c7cd0b52f4a85cc2e171b1cea931d6507", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f3133e8b8e27b301f71bba531d00a5e383c7911d8cdfb70369c15aab22a9aad5", "generation_seconds_batch": 16.70946774201002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.276410847902298, "target_z": 0.37695311473878174, "ce": 5.871703147888184, "genuineness": 4.519899368286133, "identity": -0.03014141321182251, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e1546adc3110865952f05b6584de483c7cd0b52f4a85cc2e171b1cea931d6507.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "e172379058061f9af2c2ed4d0f8f9015e9c820e840c3ca31dcd37c3e42d91afb", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ea11dc8ab0cfb10c90e551464a2355ffb5c32a5538b9ad795ba5054989915d9a", "generation_seconds_batch": 23.78177526697982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13006474077701569, "target_z": 0.028320323454543828, "ce": 6.260893821716309, "genuineness": 4.457139015197754, "identity": 0.8045397996902466, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e172379058061f9af2c2ed4d0f8f9015e9c820e840c3ca31dcd37c3e42d91afb.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "e1fa7dd7fc14707c7571d71f4cf175953658eb6424403d32b8e81404d91e02f8", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "eb59101f37517a8b09b51240af3f15c3a1fda240c2ac4826a08955b4856044fb", "generation_seconds_batch": 23.971369027043693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06324563920497894, "target_z": -0.1308593797146138, "ce": 6.181467056274414, "genuineness": 4.400654315948486, "identity": 0.6014523506164551, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e1fa7dd7fc14707c7571d71f4cf175953658eb6424403d32b8e81404d91e02f8.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": "e2061812f6ecabd475e779e194d0f964d1c025f6d13534cb31d32bada17a7e9d", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The keys are on the kitchen table.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9a7b22113dad4a8094bc9347e9f6f4cef9d7a18b3c669f9ea35d7b0af5d474b8", "generation_seconds_batch": 17.01249683299102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.980912685394287, "target_z": 4.4375000266237015, "ce": 6.197352409362793, "genuineness": 4.319066047668457, "identity": 0.4326069951057434, "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_Awe/e2061812f6ecabd475e779e194d0f964d1c025f6d13534cb31d32bada17a7e9d.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "e2391192caa8d1e6bd051a4b4116dc2b4f1f7d38bd891a2e510122730857f449", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "97ca308494e1af97eb3c17826e03892278ed1b33b4d7f0238fdd741268de3549", "generation_seconds_batch": 23.4181006179424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.125209093093872, "target_z": 4.781249924566179, "ce": 6.23706579208374, "genuineness": 4.582659721374512, "identity": 0.42188629508018494, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e2391192caa8d1e6bd051a4b4116dc2b4f1f7d38bd891a2e510122730857f449.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "e23a3fe5c777632f5f7ca5404bd954536a4901804944d8a1a38db377c97cd817", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f9d58f5d3de3a40a41a57c3cf3121de8cc22dd42f798c0ce884b5e2b8a4618d5", "generation_seconds_batch": 28.129786949953996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.151381254196167, "target_z": 0.07910155515074908, "ce": 6.268836498260498, "genuineness": 4.7081804275512695, "identity": 0.7796651124954224, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e23a3fe5c777632f5f7ca5404bd954536a4901804944d8a1a38db377c97cd817.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "e26283615ac07bd4053697586e4a750398f6201a390e55a3727ea2aad5b92997", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "756ba131529898d006c6450d0b0af765b0fe44290305dae2f1920e9471508114", "generation_seconds_batch": 22.924157557892613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4264463484287262, "target_z": 0.734374957845806, "ce": 6.260893821716309, "genuineness": 4.042920112609863, "identity": 0.34838026762008667, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e26283615ac07bd4053697586e4a750398f6201a390e55a3727ea2aad5b92997.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "e27bf6875a19cc99f4a4efa110b852bb0772e208bc582d61bd8f2ce307dfd359", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8cd421a5f5ce172d78d0706361093d0e248a3162c454f8872c9fb3a02b72e1d3", "generation_seconds_batch": 17.492174144019373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18786530196666718, "target_z": 0.166015622504028, "ce": 6.078212261199951, "genuineness": 4.15588903427124, "identity": 0.3907011151313782, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude graam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e27bf6875a19cc99f4a4efa110b852bb0772e208bc582d61bd8f2ce307dfd359.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "e289a1cdf86bbe22e1460a198e0858b06ff63cbc422686eb25fc4400c40db419", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "57c412c7e05eb613371a9963b706d8cf7d12cfa97d59ce10f46ec05e9752c2f2", "generation_seconds_batch": 24.12595344800502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6464072465896606, "target_z": 3.6406249534085227, "ce": 5.871703147888184, "genuineness": 4.419482707977295, "identity": 0.6217169165611267, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e289a1cdf86bbe22e1460a198e0858b06ff63cbc422686eb25fc4400c40db419.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": "e2c8b306772ca15cd87d21b5671415e556087c95736e14cca8a5a63d432e61e5", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1710326dda65a738d83c0f385136f53b7060edaa38e39ab608edadab344e9174", "generation_seconds_batch": 17.23968708200846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21656061708927155, "target_z": 0.23437499334407463, "ce": 5.450741291046143, "genuineness": 4.281409740447998, "identity": 0.5811800956726074, "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_Awe/e2c8b306772ca15cd87d21b5671415e556087c95736e14cca8a5a63d432e61e5.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "e2fc3338156f8fb06471a1f36c077047ab209602e5233991e57db951fb3c1142", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2dd310242bdad081a5ceb6472ad3111a38e9ff1211894bb834921a658ad5e97b", "generation_seconds_batch": 26.41349039308261, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3083856403827667, "target_z": 0.4531250155304925, "ce": 6.260893821716309, "genuineness": 4.532451152801514, "identity": 0.4665670394897461, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e2fc3338156f8fb06471a1f36c077047ab209602e5233991e57db951fb3c1142.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "e3441a253196ca406e3eb0b273062044c5327a1f8d74c2942679fbb383657548", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "dfe855a2c60df1606812bec3b1a9175291b1f7ddd2b6e89a6c65562873643d02", "generation_seconds_batch": 23.98239467293024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1151340007781982, "target_z": 2.375000070996537, "ce": 6.300607204437256, "genuineness": 4.545003414154053, "identity": 0.618263840675354, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e3441a253196ca406e3eb0b273062044c5327a1f8d74c2942679fbb383657548.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "e34455ce934cfaff56c1dfc18c6800ef1811b7ed0621de01155c47ea0183688d", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8b430a6ed2837092584a5f4288dee9431dfa3ed5d081ff5acdea9f2f5861000a", "generation_seconds_batch": 17.733103750040755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3542981445789337, "target_z": 0.5625000088745672, "ce": 6.197352409362793, "genuineness": 4.8588056564331055, "identity": 0.8271732330322266, "hypothesis": "J'ai trouvé la 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_Awe/e34455ce934cfaff56c1dfc18c6800ef1811b7ed0621de01155c47ea0183688d.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": "e34f475a2d4e0c0be352ec2075c99e6645447986fa6f205935fc70235e94930e", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7a3b4ce4f9b8de82c7887ad8afc2c129f03463310f2a6cf038239592776480f2", "generation_seconds_batch": 18.215264296974055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2463126182556152, "target_z": 2.6875001331185073, "ce": 6.086154937744141, "genuineness": 4.319066047668457, "identity": 0.5446838140487671, "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_Awe/e34f475a2d4e0c0be352ec2075c99e6645447986fa6f205935fc70235e94930e.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "e3b332009683df898bf04e072d5dd8ed8641afd9ac9d6b41e3a988a096fe6d92", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "75e13d5dda28b9024c6b8de9bbf6ded08d14f53e61d7cb600ca74fab1244ba79", "generation_seconds_batch": 23.98239467293024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2135179042816162, "target_z": 2.6093749755949402, "ce": 6.213237762451172, "genuineness": 4.632867813110352, "identity": 0.5538594126701355, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e3b332009683df898bf04e072d5dd8ed8641afd9ac9d6b41e3a988a096fe6d92.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": "e3f12502b5cb497a8466067894620a331d3b4588fef1e7751f68c091432aa5af", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6b5d06ff462bdf3436ef04c6a30a3db4bff1d3ea88c84a5ceaae1ee2a2c6d88a", "generation_seconds_batch": 17.249531714012846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6201715469360352, "target_z": 3.5781249977813583, "ce": 6.062326908111572, "genuineness": 4.6705241203308105, "identity": 0.43658560514450073, "hypothesis": "Jemand hat dem kleinen blauen Stuhl umgestellt. Er stand hier, neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e3f12502b5cb497a8466067894620a331d3b4588fef1e7751f68c091432aa5af.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "e3f2d99adb98e4da43f49f47a8e85086f301f326ef84bc951e81dc6fbf137b5b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b6092a75a803506e490c6c9daf4ae450460d2c1abb313ef843c246416fc6a61c", "generation_seconds_batch": 23.14142889797222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3709322214126587, "target_z": 2.984374993344075, "ce": 6.41180419921875, "genuineness": 4.595211505889893, "identity": 0.2410832643508911, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e3f2d99adb98e4da43f49f47a8e85086f301f326ef84bc951e81dc6fbf137b5b.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "e3f99ef1a288e5b0a11a4eae2068956dbc53a221aecfed478c2c733d73527a63", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "332020932e2987afb4cb20659b1f7eafbd0f7f6611054cfa340f669a44aca610", "generation_seconds_batch": 24.2679460500367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16613885760307312, "target_z": 0.11425783343843188, "ce": 6.308549880981445, "genuineness": 4.557555198669434, "identity": 0.7202808856964111, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e3f99ef1a288e5b0a11a4eae2068956dbc53a221aecfed478c2c733d73527a63.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "e401ad9a08dc9aa1b37d3664c82f9523390e5b70826017ef69b080332141a1e2", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "62e705807ed52776656f9e0590e311efd00717cd70db9d838bf3c71294e7abd7", "generation_seconds_batch": 18.69190172094386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19524410367012024, "target_z": 0.1835937616478694, "ce": 5.998785495758057, "genuineness": 4.507347106933594, "identity": 0.8356049656867981, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e401ad9a08dc9aa1b37d3664c82f9523390e5b70826017ef69b080332141a1e2.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "e40ace9663ce09beff3f7fa138e803c721523844ddc02b6d7f4a1425c9af3c41", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6ca620356aa34dc469d45b9c9fad008e9a5a57763306871c96d88902ea1b229b", "generation_seconds_batch": 22.404613318038173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5117124319076538, "target_z": 0.9374999556271643, "ce": 5.967014789581299, "genuineness": 4.457139015197754, "identity": 0.559204638004303, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e40ace9663ce09beff3f7fa138e803c721523844ddc02b6d7f4a1425c9af3c41.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": "e4c7d90d397d7cbc430da158c4f1db185f0c971703d27364381c7031097c2da4", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Escribí el número en el sobre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "75ac15ffbb8579e991762c17d73f70509e6c75e39bb9173c6c8c3df626906851", "generation_seconds_batch": 16.888502010027878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.941322386264801, "target_z": 1.9609376164786938, "ce": 6.205295085906982, "genuineness": 4.482243061065674, "identity": 0.49492597579956055, "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_Awe/e4c7d90d397d7cbc430da158c4f1db185f0c971703d27364381c7031097c2da4.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "e589d1728a1e8e502827050991b1cf8f08e0de75441cb21f31eaafa0077f1a4e", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9ec25f0901c509c29583967cd70913b170d53686cd4686ca542c81221995a3df", "generation_seconds_batch": 21.485125236096792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9577196836471558, "target_z": 2.000000053247403, "ce": 6.125868320465088, "genuineness": 4.582659721374512, "identity": 0.8446341753005981, "hypothesis": "J'ai trouvé la 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_Awe/e589d1728a1e8e502827050991b1cf8f08e0de75441cb21f31eaafa0077f1a4e.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": "e614afe11146312f75db6c91e3182571abad01245591297f0a868096a2087c03", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Someone moved the little blue chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2bdee5a544f44836b734c4b3c4c6d37bf2a72efc2052ad4a33c2d7138af0bc58", "generation_seconds_batch": 17.110324237961322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7841447591781616, "target_z": 3.9687499334407463, "ce": 6.221180438995361, "genuineness": 4.231201171875, "identity": 0.5144052505493164, "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_Awe/e614afe11146312f75db6c91e3182571abad01245591297f0a868096a2087c03.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "e68370b671794947a997a694e87057168c2f46d872f7ac8ada5ca68956c1234a", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0bd5eb74be8fb8cb59530160f92a13cad20bbb54bb37928338107fc0f59796f3", "generation_seconds_batch": 24.09472017304506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18622556328773499, "target_z": 0.1621093575281959, "ce": 6.268836498260498, "genuineness": 4.7081804275512695, "identity": 0.527708888053894, "hypothesis": "Die Tür 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_Awe/e68370b671794947a997a694e87057168c2f46d872f7ac8ada5ca68956c1234a.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "e6e053bdb6b2d5dcadf166875fa2e8776f1bd9a5d1b823796678cfff9182657d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "1e9d176a9eaaa035113c4f59cdeaaf09d71d0fe0c37a41ee4a8dcb8009a07785", "generation_seconds_batch": 23.138425928889774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0101910829544067, "target_z": 2.1249999645017312, "ce": 6.372091293334961, "genuineness": 4.545003414154053, "identity": 0.5040141344070435, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/e6e053bdb6b2d5dcadf166875fa2e8776f1bd9a5d1b823796678cfff9182657d.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "4a1af128fbc99ac87bb629444a940d50117978ba2ca190da04e4136f2425d404", "generation_seconds_batch": 17.417981898994185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18622556328773499, "target_z": 0.1621093575281959, "ce": 6.459460258483887, "genuineness": 4.394378662109375, "identity": 0.22044244408607483, "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_Awe/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "e6fe9487a8240e3cc22195c85143d3748fdde1a29cc10bcecf5d8db58b761d1a", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c6b7aaba045f646366d6d576a43961d7f8cd845a4670eac1ca482692424fcfbf", "generation_seconds_batch": 16.350305494037457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8234983682632446, "target_z": 4.062500008874567, "ce": 5.871703147888184, "genuineness": 4.545003414154053, "identity": 0.4605149030685425, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e6fe9487a8240e3cc22195c85143d3748fdde1a29cc10bcecf5d8db58b761d1a.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "e764ec58333e45757292e5da0772c8b7785f9ec13050fbe02f6f2cfa4a8fbde6", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "46b6bc062bf211dd3ed542263d271b1e846a3065925c4cf20cb72ff7ff97117a", "generation_seconds_batch": 21.625705752987415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1676054000854492, "target_z": 2.499999982250866, "ce": 6.229123115539551, "genuineness": 4.645420074462891, "identity": 0.6625838279724121, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e764ec58333e45757292e5da0772c8b7785f9ec13050fbe02f6f2cfa4a8fbde6.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "e78786db693b782782f36faaa753c9054c831244e0f48a78bd57e77fcbc64935", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "675b617bc44e6d2f8a34041885c923cf4e8769a6fc46b73ea1e2b679a158daa3", "generation_seconds_batch": 22.240110952057876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4953151047229767, "target_z": 0.898437447861918, "ce": 6.09409761428833, "genuineness": 3.653805732727051, "identity": 0.15894295275211334, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e78786db693b782782f36faaa753c9054c831244e0f48a78bd57e77fcbc64935.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "e828767b29f25ab84da0ff0d12ee77a937cf8c0b4cb93a0a2a57ce2d1345260c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1a658e8b2ed2631e3c5216c8ac980cec458fb1f45445ce89d24639efc59a865e", "generation_seconds_batch": 23.32593015593011, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4034900963306427, "target_z": 0.6796874611737687, "ce": 6.38003396987915, "genuineness": 4.632867813110352, "identity": 0.7594125270843506, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e828767b29f25ab84da0ff0d12ee77a937cf8c0b4cb93a0a2a57ce2d1345260c.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "e869b631c809271e13a28282a4a567eb7d1052379b3b00847f7c5e23bef1e3ed", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "071df82d91f7b677c249fae95f2781c569fbc14411cf940f0cf8e06f9b0fdb61", "generation_seconds_batch": 23.59453741798643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5152287483215332, "target_z": 3.3281251752727012, "ce": 6.324435234069824, "genuineness": 4.632867813110352, "identity": 0.6050792932510376, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e869b631c809271e13a28282a4a567eb7d1052379b3b00847f7c5e23bef1e3ed.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "e870348b54448deb988da2c651f6f4fb3ac5c3b873c8cbf8806e3d4de53ed12d", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "be148c5339e81e10a4c42cd4effbbc5e44b435f4df3e893a5e53076f6058f34a", "generation_seconds_batch": 24.034011828014627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.99051433801651, "target_z": 2.0781250687778954, "ce": 6.109982967376709, "genuineness": 4.432034492492676, "identity": 0.278997540473938, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e870348b54448deb988da2c651f6f4fb3ac5c3b873c8cbf8806e3d4de53ed12d.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "e8abdbaed3b7fdb1c502c35baee7e03b04f69e0e8ca977bd4968b47a33171dec", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "10b62827b0945422ed1df6ab8cdfc72a572dacaefdad3c4c8022609db7f2908a", "generation_seconds_batch": 23.469037280068733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2755909860134125, "target_z": 0.375, "ce": 5.728734970092773, "genuineness": 4.406930446624756, "identity": 0.32707035541534424, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e8abdbaed3b7fdb1c502c35baee7e03b04f69e0e8ca977bd4968b47a33171dec.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "e918636887ede2ed273a8863b540747cc7e0e36dc19cfe7afc6a928a33a1d117", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "15ce225b0bc4d7b24993eef855f36383f29873b2e2e043722f69b8f9748f988a", "generation_seconds_batch": 23.737578265951015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13498392701148987, "target_z": 0.04003904738550282, "ce": 6.157639026641846, "genuineness": 4.6705241203308105, "identity": 0.4838380515575409, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e918636887ede2ed273a8863b540747cc7e0e36dc19cfe7afc6a928a33a1d117.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "e9207673bf796935af591f281cf2c66201e9bab4d37261f596019f40c4c0de06", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "fe72b01c5e6a4f8b3b3d062f522b60857d331cca5db7d750753c0b35e718da26", "generation_seconds_batch": 18.20630815590266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0101910829544067, "target_z": 2.1249999645017312, "ce": 6.372091293334961, "genuineness": 4.65797233581543, "identity": 0.6026332974433899, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/e9207673bf796935af591f281cf2c66201e9bab4d37261f596019f40c4c0de06.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "e95e6a24795f7c4e4a17b26220ceb388e33c5a0e780a2e54842c847fb9854ca9", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4762fb0a55f1e39f1860ae59b3a0d95ff65284517c215c94c1147d97850101b9", "generation_seconds_batch": 23.52375392697286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6953625082969666, "target_z": 1.3750000709965373, "ce": 5.919358730316162, "genuineness": 4.419482707977295, "identity": 0.5769755244255066, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/e95e6a24795f7c4e4a17b26220ceb388e33c5a0e780a2e54842c847fb9854ca9.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "8a6276be4507b0e104c83faa4036e3edb636ad9484102746484f1e99dba0a721", "generation_seconds_batch": 18.17946313205175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48219725489616394, "target_z": 0.8671874700483359, "ce": 6.443574905395508, "genuineness": 4.532451152801514, "identity": 0.46915751695632935, "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_Awe/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "ea2d2a7ad7fcec18bced4e28573690543408c7e7c7a1fb89617233348f853617", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5110608a3bb50f40b48113ed20699c2de26becd35d7b00b9401e7df42b495948", "generation_seconds_batch": 23.87988481298089, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6527294516563416, "target_z": 1.2734375366075894, "ce": 5.95112943649292, "genuineness": 4.519899368286133, "identity": 0.77021723985672, "hypothesis": "J'ai trouvé la 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_Awe/ea2d2a7ad7fcec18bced4e28573690543408c7e7c7a1fb89617233348f853617.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "eac3a4f0d4379cb1cc963ea8a25fa7d6845f33373a7d855eaf2e03c8b32038a5", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "bb2362ed6fd8859d2ccf6b7ad86af62a584a2955a31b1e79903feee52b3061ea", "generation_seconds_batch": 29.54347494605463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34118029475212097, "target_z": 0.531250031060985, "ce": 6.284721851348877, "genuineness": 4.15588903427124, "identity": 0.2167966663837433, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/eac3a4f0d4379cb1cc963ea8a25fa7d6845f33373a7d855eaf2e03c8b32038a5.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "ead3250857e2fee318168e49ff139c5e6accbe23998ec41ad29746c80be6129f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2afbddbc0366fc242c7a740ed4e8c78bd0ff21089b9de741c3506640601c1264", "generation_seconds_batch": 23.889998727012426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9839553833007812, "target_z": 2.0625000088745673, "ce": 5.982900142669678, "genuineness": 4.570107460021973, "identity": 0.885521411895752, "hypothesis": "J'ai trouvé la 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_Awe/ead3250857e2fee318168e49ff139c5e6accbe23998ec41ad29746c80be6129f.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "eadea131e0943dfe92aed5d9253a0bfc105ac20ae8139d4fb2acfb647ee1f1df", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9411c8855fa175a776568535729b58ace096500fcaec3c23225082b3c4896ded", "generation_seconds_batch": 23.895570373977534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5740222930908203, "target_z": 1.0859375277330223, "ce": 6.292664527893066, "genuineness": 4.319066047668457, "identity": 0.43853458762168884, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/eadea131e0943dfe92aed5d9253a0bfc105ac20ae8139d4fb2acfb647ee1f1df.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "eb0f5dc2baef4bfedf4674dd65bcf99a8d68758e78dbb81b6de8e9c24f8ac0cc", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "afa0ff0f439d6d2ff3b1d3f615e29367e0426a27dccc222117c7b201d96867be", "generation_seconds_batch": 18.096543646068312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.46088072657585144, "target_z": 0.816406202853862, "ce": 6.09409761428833, "genuineness": 4.507347106933594, "identity": 0.500595211982727, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/eb0f5dc2baef4bfedf4674dd65bcf99a8d68758e78dbb81b6de8e9c24f8ac0cc.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "eb887fc4bb55b452f8d28f7963aa48d4de9e8b1340008b0e6c867ec660fe64e2", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "819f41045b5e6cdd0307ca77817b88223545dfdb3765e77e8fa437f5183a4cda", "generation_seconds_batch": 23.87988481298089, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3985708951950073, "target_z": 0.6679687017445411, "ce": 6.078212261199951, "genuineness": 4.607763767242432, "identity": 0.8435497283935547, "hypothesis": "J'ai trouvé la 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_Awe/eb887fc4bb55b452f8d28f7963aa48d4de9e8b1340008b0e6c867ec660fe64e2.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "eb8c0645896546ca2d4a008b2ea943a2f8f5b82b62128e7b54cf627debc4638c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "16b4d63545c7d01ca8992707f6ee679563aa1b2aedfe426327e6c3b73a2adb50", "generation_seconds_batch": 24.703545121941715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23377782106399536, "target_z": 0.27539065134637125, "ce": 6.221180438995361, "genuineness": 4.017816066741943, "identity": 0.3745687007904053, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/eb8c0645896546ca2d4a008b2ea943a2f8f5b82b62128e7b54cf627debc4638c.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "ebbe573de81f28cf2844361b99854db974781f699ab25d721b8b274989f9f620", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "57020c222d7ec877975ce9bd832276455ed9342fc26f5688bb2094cde21d26ff", "generation_seconds_batch": 22.735881231026724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.764231264591217, "target_z": 1.5390625610126492, "ce": 6.078212261199951, "genuineness": 4.582659721374512, "identity": 0.8124109506607056, "hypothesis": "J'ai trouvé la 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_Awe/ebbe573de81f28cf2844361b99854db974781f699ab25d721b8b274989f9f620.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "61172575753ed424e3e71f0dfaca34a166b0cdc522f753dcf3a05e68ea59b97e", "generation_seconds_batch": 18.96747257001698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08620189130306244, "target_z": -0.07617188304257648, "ce": 6.165581703186035, "genuineness": 4.369274139404297, "identity": 0.6508659720420837, "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_Awe/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "ec140e3c60b5c7e8934b724c1fb7f866811b448e5e68ad415067fe19af5b1128", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "beb9063822442668c13dd1198c5e3ad0f55d10e26ad8e41d7988dc8dc7846716", "generation_seconds_batch": 24.765843049972318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1085749864578247, "target_z": 2.3593748691001344, "ce": 6.356205940246582, "genuineness": 4.300237655639648, "identity": 0.40007883310317993, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ec140e3c60b5c7e8934b724c1fb7f866811b448e5e68ad415067fe19af5b1128.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "ec27a1601d4555c6a2b1908b8f816934e18b5fa629923ff401644254b17e64b7", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "76c1d667595dd13f8f616ae99d2a6b223f3b8562d7a3eddff8e23aba21f160d3", "generation_seconds_batch": 24.423128824913874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.282623529434204, "target_z": 5.156250226301462, "ce": 5.967014789581299, "genuineness": 4.425758361816406, "identity": 0.5601029992103577, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ec27a1601d4555c6a2b1908b8f816934e18b5fa629923ff401644254b17e64b7.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "ec647b54e6d961126cab5fe293f2f5d44b93e6ac53301f6591385d0ae6d7e0a4", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "00c69311181fbefe71788a59bab79a98cd8361f3f3e7bca125395eb7d3032d56", "generation_seconds_batch": 21.94421207997948, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.059619903564453, "target_z": 4.625000177491343, "ce": 5.974957466125488, "genuineness": 4.482243061065674, "identity": 0.5991867780685425, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ec647b54e6d961126cab5fe293f2f5d44b93e6ac53301f6591385d0ae6d7e0a4.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "ec9e05de3ad24cef840f4a7410960831e31181d6b151cb691e25ab57dbd625c0", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0491eb588a4ad263c764f3bcb7cc93aea73b7cc1cf45140eaa9cb8156152ccd7", "generation_seconds_batch": 23.062302823062055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8658946752548218, "target_z": 1.7812500665592537, "ce": 6.205295085906982, "genuineness": 4.808597087860107, "identity": 0.806105375289917, "hypothesis": "J'ai trouvé la 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_Awe/ec9e05de3ad24cef840f4a7410960831e31181d6b151cb691e25ab57dbd625c0.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "ecd84cba77e91b92b24bd3f0550bc46be8e88f667588093ef0b174bc8cdd301c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "11ea27b479579479c81def9a557c42f8fe56860b1ba7dc6c741def9b2bef4288", "generation_seconds_batch": 22.768610117956996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3624967932701111, "target_z": 0.5820312272589216, "ce": 6.3641486167907715, "genuineness": 4.287685871124268, "identity": 0.7076351642608643, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ecd84cba77e91b92b24bd3f0550bc46be8e88f667588093ef0b174bc8cdd301c.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "ecf0be7b111bc3deda8cb7c341675eb6d77b77cf7dbb5df4d2c7342a83013de4", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1a5386f920cb21ed136a15c22b7809c3871612a8afa3abf3ceb2acc74186bf99", "generation_seconds_batch": 29.514304826036096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.177680492401123, "target_z": 4.906249835820508, "ce": 6.038498878479004, "genuineness": 4.582659721374512, "identity": 0.4687495231628418, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ecf0be7b111bc3deda8cb7c341675eb6d77b77cf7dbb5df4d2c7342a83013de4.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "ed0ae8952fb5cf71551d0c14bb1ae55229d0e5182c6fd8aeb14338c897f8be9f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "76a68055d26233034a041c629337d3d222953476b563848645bcef9d79b505c4", "generation_seconds_batch": 31.063843147014268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45432180166244507, "target_z": 0.8007812139470709, "ce": 6.300607204437256, "genuineness": 4.65797233581543, "identity": 0.5053432583808899, "hypothesis": "Die Tür 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_Awe/ed0ae8952fb5cf71551d0c14bb1ae55229d0e5182c6fd8aeb14338c897f8be9f.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "ed73ca53c292cd5fe5e440d1959ab39b126b10b6ff458a68b360567ebb9bf27f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "06559039692f3ac62a0fa57e39ed9150f3d085472da91541bd52a1c3ec3aa305", "generation_seconds_batch": 24.46514968504198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34609946608543396, "target_z": 0.5429687194936754, "ce": 6.157639026641846, "genuineness": 4.6705241203308105, "identity": 0.5392114520072937, "hypothesis": "Die Tür 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_Awe/ed73ca53c292cd5fe5e440d1959ab39b126b10b6ff458a68b360567ebb9bf27f.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "ed7a388a2c4b8b31e97b8fa40b5e7dbf1a9f514d2223bdf66356e683a626f7b6", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "abe097c371b06f5c943d4bfea82985cf68d2fbc602a34504e571dd1bfddb219a", "generation_seconds_batch": 23.549126597936265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7019214034080505, "target_z": 1.390624988906791, "ce": 6.324435234069824, "genuineness": 4.243753433227539, "identity": 0.37177422642707825, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ed7a388a2c4b8b31e97b8fa40b5e7dbf1a9f514d2223bdf66356e683a626f7b6.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "ee6500513ae89f92a1724829ec9b9c181ae763d57c96ef522d46784fb0b1ec20", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "71084ba0e6023421e3735f10110e6fdb47e6a6a6efa28a4aeb5195a2e8cf265a", "generation_seconds_batch": 18.349288161029108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1796666383743286, "target_z": 0.14648436862140485, "ce": 6.252951145172119, "genuineness": 4.093128204345703, "identity": 0.43049514293670654, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ee6500513ae89f92a1724829ec9b9c181ae763d57c96ef522d46784fb0b1ec20.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "eeea0812366b9d17ed185d7c869955bc6476e4dc92073df01821a1fcc9d5ab32", "bucket": "emo_Awe", "phase": "wording", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3f7a302cf38c98e28855cdf80361927f35c82fe53d22eaf3be01f9b4d9aefe17", "generation_seconds_batch": 17.97626573208254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3149445652961731, "target_z": 0.4687500044372836, "ce": 6.181467056274414, "genuineness": 4.080576419830322, "identity": 0.24297910928726196, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/eeea0812366b9d17ed185d7c869955bc6476e4dc92073df01821a1fcc9d5ab32.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "efa7e1b9a7f45fa256aeeba6428d43e8ff124c5c996856093b2b5bdff1e7347f", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b1c273209cf5a5492fb5dc352fdb338598ed987c8451120947cddfb2659a8a37", "generation_seconds_batch": 21.563694206997752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8822919726371765, "target_z": 1.8203125033279626, "ce": 6.300607204437256, "genuineness": 4.331617832183838, "identity": 0.3484645485877991, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/efa7e1b9a7f45fa256aeeba6428d43e8ff124c5c996856093b2b5bdff1e7347f.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "f0ed2e223c1632682673de2aa300ed1ee1a738ec53514d158894152777ea584c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "00bca6eecd6fef4b43d5bbd470e6b0553aa7c2eb6274f0bab41d38d3d5f59499", "generation_seconds_batch": 21.801287107984535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4693162441253662, "target_z": 3.218750181928627, "ce": 5.728734970092773, "genuineness": 4.3504462242126465, "identity": 0.5556007623672485, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/f0ed2e223c1632682673de2aa300ed1ee1a738ec53514d158894152777ea584c.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "f15debe3b7fd124c15602d44b7e052a7d426c59a2a74fd09f58c659dbf30f568", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b671e34c3306fd851389540ef089e4989fa70e2d0c8718e99e01d4c5d6d132a6", "generation_seconds_batch": 22.781671465956606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3119019269943237, "target_z": 2.8437501641794922, "ce": 5.77639102935791, "genuineness": 4.519899368286133, "identity": 0.37928810715675354, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/f15debe3b7fd124c15602d44b7e052a7d426c59a2a74fd09f58c659dbf30f568.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "39d636f8f1e5215957932128af74b178de906daa58b1c871a104ac8444626bc6", "generation_seconds_batch": 19.15486834803596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15589052438735962, "target_z": 0.08984375721058581, "ce": 6.356205940246582, "genuineness": 4.607763767242432, "identity": 0.6406611800193787, "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_Awe/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.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": "f22c55aa7c18ace00db208eb7b7ca87a12e91d193d9ea08feca0f43d71727d8d", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Escribí el número en el sobre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "804f4940095bdabd507b3bdf762895251d82a25b5c3fc1285d1f8257641e9f3e", "generation_seconds_batch": 17.504039866034873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3709322214126587, "target_z": 2.984374993344075, "ce": 6.1894097328186035, "genuineness": 4.607763767242432, "identity": 0.5943412780761719, "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_Awe/f22c55aa7c18ace00db208eb7b7ca87a12e91d193d9ea08feca0f43d71727d8d.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "f235bae7cf9c767918881003badf64f61e475f27778b284a58cf610de88914d9", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "87ccdc2e3e4dbe200bfae0794315854d6e06de3fb539a7cffc1c8d122f377443", "generation_seconds_batch": 16.870462088962086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4100490212440491, "target_z": 0.6953124500805598, "ce": 6.427689552307129, "genuineness": 4.174716949462891, "identity": 0.45610982179641724, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/f235bae7cf9c767918881003badf64f61e475f27778b284a58cf610de88914d9.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "f240501cc249a3f177e12680fd043d6cc25e146c62b3e4d005c903e651eca575", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4fedd15cd41d180a938ec244f802b5f8bec4b16bdd8d856710ff3bf7ad056fb3", "generation_seconds_batch": 18.164114561048336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5707428455352783, "target_z": 1.0781250687778954, "ce": 6.268836498260498, "genuineness": 4.444586753845215, "identity": 0.6249028444290161, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/f240501cc249a3f177e12680fd043d6cc25e146c62b3e4d005c903e651eca575.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "f4baeff161d4964302110754a51b0d219abe83fc2d743114838e48baf461f341", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "22d1aa1b9894c28ef033eb89f83105aad697de42ac8200905f21c36bf7a80eae", "generation_seconds_batch": 16.379619634943083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.007148265838623, "target_z": 4.499999698264717, "ce": 5.6532793045043945, "genuineness": 4.344170093536377, "identity": 0.49553924798965454, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/f4baeff161d4964302110754a51b0d219abe83fc2d743114838e48baf461f341.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": "f54e6864fc98c562bea08dd33be401818013d498358725189daf10040664b52a", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "da93c1de41aafe7df0abf27ad7ca555780a7a6e67e0ae91c62226ef33cf93960", "generation_seconds_batch": 17.25504364608787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.098973274230957, "target_z": 4.718749684952866, "ce": 6.300607204437256, "genuineness": 4.168440818786621, "identity": 0.682814359664917, "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_Awe/f54e6864fc98c562bea08dd33be401818013d498358725189daf10040664b52a.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": "f577c0fc529bafdc0cda0422fa450ed9a6f028ba003be18e55c09f94b56ba129", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9e3dddc6b40d43a6209298d3f342c2dde0ff9a04b2700999224dc4a7dab476cf", "generation_seconds_batch": 24.728964876034297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8199821710586548, "target_z": 1.671875073215179, "ce": 5.6254801750183105, "genuineness": 4.369274139404297, "identity": 0.7528754472732544, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/f577c0fc529bafdc0cda0422fa450ed9a6f028ba003be18e55c09f94b56ba129.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "f59551766887b45b645c9b0e67407c799464be29d670b0127be916a736bf9691", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a60c1041ba35564972f8f8ee1a82a7e3f4286f14803744c398d1eab0bd83f34e", "generation_seconds_batch": 21.99769961705897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23131820559501648, "target_z": 0.26953123613348884, "ce": 6.006728172302246, "genuineness": 4.18099308013916, "identity": 0.5520615577697754, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/f59551766887b45b645c9b0e67407c799464be29d670b0127be916a736bf9691.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "f6df0b05142bc83428ddf08a9d22a9a7c04558e54068135ccaef0e9c4720d941", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d2e6249962f0f9180987e57ac46ab2189543152c35a4d4739cc70b7f2a09f70b", "generation_seconds_batch": 25.16346226306632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08866149187088013, "target_z": -0.07031250332796268, "ce": 6.09409761428833, "genuineness": 4.6203155517578125, "identity": 0.7124074697494507, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/f6df0b05142bc83428ddf08a9d22a9a7c04558e54068135ccaef0e9c4720d941.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "f6e299701421fd3b614e0082edf7598a89d0a59ec42096f373de2c953b7e8e58", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a4688840eedee2853acb98b2e23b8328dad67aada5a7e4b20ad650ea6deced16", "generation_seconds_batch": 17.656719321967103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1413697004318237, "target_z": 2.4375000266237015, "ce": 5.847874641418457, "genuineness": 4.319066047668457, "identity": 0.46380674839019775, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/f6e299701421fd3b614e0082edf7598a89d0a59ec42096f373de2c953b7e8e58.mp3" }, { "id": "emo_Awe-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-0", "key": "f739a3ecbfd42f7b041dfb88ca7115efee200e1797ab812a771826dcc33c8439", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The door is still open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I put your coat on the chair.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d72f868cca5fc7342b21500da6ce6972efec945aafef5e1fe0164aa93436d802", "generation_seconds_batch": 24.210201211972162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5412276387214661, "target_z": 1.0078125122025299, "ce": 6.1020402908325195, "genuineness": 4.419482707977295, "identity": 0.4849511682987213, "hypothesis": "The door is still open. I put your coat on the chair. T Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/f739a3ecbfd42f7b041dfb88ca7115efee200e1797ab812a771826dcc33c8439.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "f7a09dfff8c603ccfad6286d1c4de1fb9ed2a8fa4ebb71236fa4513cbdaa9628", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "69bf8696ab89776c27e605bf5823072770f4fbea23dbf34e2e02a0605623023c", "generation_seconds_batch": 24.080585200106725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3985708951950073, "target_z": 0.6679687017445411, "ce": 6.117925643920898, "genuineness": 4.595211505889893, "identity": 0.689858078956604, "hypothesis": "J'ai trouvé la 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_Awe/f7a09dfff8c603ccfad6286d1c4de1fb9ed2a8fa4ebb71236fa4513cbdaa9628.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "78e10fe3fcd5d0667f522b67107fea23225eb77974dd13e8104687a6345426c8", "generation_seconds_batch": 18.76254422101192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.173517644405365, "target_z": 0.13183593708400468, "ce": 6.09409761428833, "genuineness": 4.432034492492676, "identity": 0.5202741026878357, "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_Awe/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "f7fe71039eac4551cecd5679451ba36a2570306d3dd934135840433c508f6efb", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "62bbbb98a5de4f9082790d976b35eacd0791a316363917bff8c3848d9cc40219", "generation_seconds_batch": 16.81614069303032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8497340679168701, "target_z": 4.124999964501732, "ce": 5.470598220825195, "genuineness": 4.331617832183838, "identity": 0.3801719546318054, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/f7fe71039eac4551cecd5679451ba36a2570306d3dd934135840433c508f6efb.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_Awe", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": "b88d624c86d7373cfc120dad6f6b9d1dd54a22c3fbd99a75d437865f5594cc53", "generation_seconds_batch": 16.32373954798095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1062886193394661, "target_z": -0.028320305705409523, "ce": 6.300607204437256, "genuineness": 4.20609712600708, "identity": 0.4622536301612854, "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_Awe/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "f8dfcb06c4caf60f4d9dc9bb0ec48e8770fa61c6c3f2a36e25913fe8415bc61a", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3b42909762c5c0e2001ef7cd5aedb5ccefc039b6d0b752e8c612ab9f63e30fc2", "generation_seconds_batch": 24.12595344800502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.282623529434204, "target_z": 5.156250226301462, "ce": 5.903473377227783, "genuineness": 4.645420074462891, "identity": 0.4376075267791748, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/f8dfcb06c4caf60f4d9dc9bb0ec48e8770fa61c6c3f2a36e25913fe8415bc61a.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "f95eecd89c6944719dceba4af8df5efa44eb641aef9c93904cb6d903cfb20166", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "4a87c5330cec7f96a8e7740aa5eed82ed67b5b973bd09cc60e064fd4ea20cf66", "generation_seconds_batch": 23.59453741798643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3643733263015747, "target_z": 2.968750075433821, "ce": 6.395919322967529, "genuineness": 4.632867813110352, "identity": 0.5714215636253357, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/f95eecd89c6944719dceba4af8df5efa44eb641aef9c93904cb6d903cfb20166.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "f9c05c1f8699a40fc7fbe2e99bc81bbc5aacbc0844f2dcb2d2a7850418868842", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8d29d35a62afc56de19cb10c04eae2739c5bd8e7a47d8e5e51f5a177d0cc5a20", "generation_seconds_batch": 16.350305494037457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8497340679168701, "target_z": 4.124999964501732, "ce": 5.911416053771973, "genuineness": 4.532451152801514, "identity": 0.4587482511997223, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/f9c05c1f8699a40fc7fbe2e99bc81bbc5aacbc0844f2dcb2d2a7850418868842.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "fa054b58bb0a6716db986350001029498e47a0471c4df386095425158bfeb782", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "43abef2f5f68a83e894fca64aad521dc012069fc902609c6568f071eabd43c8f", "generation_seconds_batch": 24.27643874497153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0561035871505737, "target_z": 2.234374957845806, "ce": 6.070269584655762, "genuineness": 4.545003414154053, "identity": 0.7011561393737793, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/fa054b58bb0a6716db986350001029498e47a0471c4df386095425158bfeb782.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "fa1928a294f97abfbf8135b034c4a02161c5c7fb2209cc0f07fc622b07676a57", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e841cd37b1a7dfa614c470b7c4a56e96cc3c2393dc70e954f2b8a4c70c7b2205", "generation_seconds_batch": 23.604537803097628, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09317075461149216, "target_z": -0.05957031901726025, "ce": 6.292664527893066, "genuineness": 4.532451152801514, "identity": 0.57961505651474, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/fa1928a294f97abfbf8135b034c4a02161c5c7fb2209cc0f07fc622b07676a57.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": "fa4b8bc94ef5c00d2f973059a0d66da773b3197eecd92eabdd93b472ca11fa42", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5a3b8dd4d5d0bb3fb38e147d2761004b4e48b004bd871ff89839f1861e889eed", "generation_seconds_batch": 17.37614841503091, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10710848122835159, "target_z": -0.026367190966627794, "ce": 6.316492557525635, "genuineness": 4.507347106933594, "identity": 0.6924982666969299, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, ließ sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/fa4b8bc94ef5c00d2f973059a0d66da773b3197eecd92eabdd93b472ca11fa42.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": "fa7bb242d0690330d56224a867692413f098143e967675dce2635b213aff8720", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The road turns left behind the bridge.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "31f41a37de703e21ee27bc41bf6b3dadd796d954d78dbb032406d0bb7c7760e7", "generation_seconds_batch": 17.217853924026713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1348108053207397, "target_z": 2.4218751087134476, "ce": 6.078212261199951, "genuineness": 4.193545341491699, "identity": 0.5181485414505005, "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": 0.120000000000001, "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_Awe/fa7bb242d0690330d56224a867692413f098143e967675dce2635b213aff8720.mp3" }, { "id": "emo_Awe-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-0", "key": "fa7fc509e121afc20485f7e59a4afdb47b060badeef0961da8c36aebc21e8b28", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La puerta sigue abierta.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a40694480e1ff12f529b4d91c2dc60644a9606d8baf2d6ca354be6f574e71762", "generation_seconds_batch": 17.255804802989587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43628475069999695, "target_z": 0.7578124767042612, "ce": 6.133810997009277, "genuineness": 4.218649387359619, "identity": 0.42612072825431824, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/fa7fc509e121afc20485f7e59a4afdb47b060badeef0961da8c36aebc21e8b28.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "fa8d6e748e4b811a0b1177cb37821cb2247cdf3b3331b03e9ef21ce995dd3423", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "60188af199324c1be6101c462c2e98fe2caef01e7c34ff7d59a6da1ee9922702", "generation_seconds_batch": 23.877082450082526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12309587001800537, "target_z": 0.011718741680093295, "ce": 6.046441555023193, "genuineness": 4.469690799713135, "identity": 0.40000927448272705, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/fa8d6e748e4b811a0b1177cb37821cb2247cdf3b3331b03e9ef21ce995dd3423.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "fabeb9731db3e5cd804a5c9ca5a30016199229bf8f208a67d37c113686788ead", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "05bfe82428c6fa88893e0f37b6155dbf898ae25b7270c045c38460c3c7e298de", "generation_seconds_batch": 25.901887829997577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8298205733299255, "target_z": 1.6953125920736343, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.5915904641151428, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/fabeb9731db3e5cd804a5c9ca5a30016199229bf8f208a67d37c113686788ead.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "fac7a7c3dcc145b2b3b3a4a59a94a2e3a8a58b13893c5e04b77741611efa614c", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "29657d9ad5f924deaee1959a08bdff62b1522d74cf97f3a19b735b300e35c3db", "generation_seconds_batch": 19.28655435994733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8822919726371765, "target_z": 1.8203125033279626, "ce": 6.23706579208374, "genuineness": 4.607763767242432, "identity": 0.5532986521720886, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/fac7a7c3dcc145b2b3b3a4a59a94a2e3a8a58b13893c5e04b77741611efa614c.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": "fafb540d2c139442429b5adbc20e8159f709b53dfb50d1a0377196458cf56f0b", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] The keys are on the kitchen table.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "42454ef8c3a0c7e851c4bf711eec0431541a8cd212d675fe44823f5c3eb8f8c9", "generation_seconds_batch": 23.051724942051806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.295741319656372, "target_z": 5.18750006212197, "ce": 6.2767791748046875, "genuineness": 4.369274139404297, "identity": 0.36552709341049194, "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_Awe/fafb540d2c139442429b5adbc20e8159f709b53dfb50d1a0377196458cf56f0b.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "fafcd3fbb575ef793316694a8021ea8cfc2dea3e8227eb321db9578ecc1fc767", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "78cf6674b0bce2dffd9da7e7d04a2b2e9d68cb2a7234eeed833aad3f6b92bedd", "generation_seconds_batch": 28.34590965299867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3083856403827667, "target_z": 0.4531250155304925, "ce": 6.149696350097656, "genuineness": 4.7834930419921875, "identity": 0.5710123777389526, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/fafcd3fbb575ef793316694a8021ea8cfc2dea3e8227eb321db9578ecc1fc767.mp3" }, { "id": "emo_Awe-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-en-1", "key": "fb04b6adbee0819fdd68d42c78cd168c80e7233fee7a150c82e7e4c60bf36f66", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] I found the little box.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] It was beside the old window.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "ef2e655a9f28d64bc95ee21d38bc2fa985c3e130a4689ff8b74d2324207c5e95", "generation_seconds_batch": 22.6599802140845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.702394962310791, "target_z": 6.156250084308388, "ce": 5.692992687225342, "genuineness": 4.406930446624756, "identity": 0.5075148344039917, "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_Awe/fb04b6adbee0819fdd68d42c78cd168c80e7233fee7a150c82e7e4c60bf36f66.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": "fb744d57130824adc0cd1e3c6c1ed77e5cbacaf693119016f6b118a8fe5fc993", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ee94e16c35046bd98b6fdfc5125449db3efb14aeb0410b57d15f19a4a265b9a2", "generation_seconds_batch": 18.14836577803362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6625678539276123, "target_z": 1.2968750554660446, "ce": 6.149696350097656, "genuineness": 4.507347106933594, "identity": 0.23934611678123474, "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_Awe/fb744d57130824adc0cd1e3c6c1ed77e5cbacaf693119016f6b118a8fe5fc993.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "fbd212b22c1f47db162b1f174a7c97828e5b54d33ed1b0b0c2cf5f62b8eb3414", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "871bad4cf3d6834aecb0fd60f7a72a7e5dcbeeeb515ccafd8bdba918822b336f", "generation_seconds_batch": 24.495312712038867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3165842890739441, "target_z": 0.472656233914847, "ce": 6.157639026641846, "genuineness": 4.331617832183838, "identity": 0.5509632229804993, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/fbd212b22c1f47db162b1f174a7c97828e5b54d33ed1b0b0c2cf5f62b8eb3414.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "fbf8f8c342ce795b171c44c2463189e87d8bdffbfefc1d57bfcac39047586890", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "23ee6e54e116214f7e6daa55930613cb3020a75a10f4347b353ca360a8c3d22f", "generation_seconds_batch": 25.28146181302145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8298205733299255, "target_z": 1.6953125920736343, "ce": 6.443574905395508, "genuineness": 4.494794845581055, "identity": 0.5938016772270203, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/fbf8f8c342ce795b171c44c2463189e87d8bdffbfefc1d57bfcac39047586890.mp3" }, { "id": "emo_Awe-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-0", "key": "fc094413ebfd2b4581a93162f7970a78f418fff2503956e3a8afe4fc6094a07b", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Die Tür ist noch offen.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0654e705bd0a05108ab53a9a6ae1f605724fc5044d0decbd8d8684f0f939120c", "generation_seconds_batch": 27.271128027001396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06324563920497894, "target_z": -0.1308593797146138, "ce": 6.332377910614014, "genuineness": 4.6203155517578125, "identity": 0.45303478837013245, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/fc094413ebfd2b4581a93162f7970a78f418fff2503956e3a8afe4fc6094a07b.mp3" }, { "id": "emo_Awe-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-1", "key": "fc5d87cdc928a9236645df7bfc06380ec4a0fe4d94023063682a782fddd1ec1a", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0a503fa4a58324a0b1833a52c200b7b58de079bfb0caa047663c29a0582a83d3", "generation_seconds_batch": 22.822796534048393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.767510712146759, "target_z": 1.546875019967776, "ce": 5.593709468841553, "genuineness": 4.582659721374512, "identity": 0.6097071766853333, "hypothesis": "J'ai trouvé la petite boîte elle était près de la près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/fc5d87cdc928a9236645df7bfc06380ec4a0fe4d94023063682a782fddd1ec1a.mp3" }, { "id": "emo_Awe-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-0", "key": "fd01da3d53d1e625d32b6b10c51af71cdb9cd2a9419d38d6cfe758845fe36ac6", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De deur staat nog open.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1a490cae8e33a61ca63ace1f189f0297b0e2d3f6328fefc447af15298a070975", "generation_seconds_batch": 17.889424997963943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1284250020980835, "target_z": 0.02441405847871176, "ce": 6.157639026641846, "genuineness": 4.469690799713135, "identity": 0.7253268957138062, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/fd01da3d53d1e625d32b6b10c51af71cdb9cd2a9419d38d6cfe758845fe36ac6.mp3" }, { "id": "emo_Awe-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-de-1", "key": "fd06b64835e0fd5fb36991e6a902bb57aded2f3abfcbd7d19a6d0556217decc9", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "5ceb7d2449a0f83811d6ced7b80f27fedd36f26fb563baacf757c80a68e154f3", "generation_seconds_batch": 27.450073151965626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6297731995582581, "target_z": 1.2187500399355522, "ce": 6.395919322967529, "genuineness": 4.394378662109375, "identity": 0.4945472180843353, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Awe/fd06b64835e0fd5fb36991e6a902bb57aded2f3abfcbd7d19a6d0556217decc9.mp3" }, { "id": "emo_Awe-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-fr-0", "key": "fde5997a44209b9399df102afc571986d1d576ed17e95218168edb78c5d05f36", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] La porte est encore ouverte.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "9da9b6e11327a12e505389cfa0506cad14f3dfd0929765465281af2d9312a633", "generation_seconds_batch": 25.95774943905417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32150349020957947, "target_z": 0.48437499334407463, "ce": 6.149696350097656, "genuineness": 4.7332844734191895, "identity": 0.6797102689743042, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/fde5997a44209b9399df102afc571986d1d576ed17e95218168edb78c5d05f36.mp3" }, { "id": "emo_Awe-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-es-1", "key": "fe0beff20f08743f5c48f3b1723f6b6b614cd8de971f1fca5debc15a9a6596e2", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] He encontrado la cajita.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5e8baec5383592424cd4fc27e6d8e9581d166e6496e87eda84a3104382e66bf3", "generation_seconds_batch": 21.758353341021575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.203916311264038, "target_z": 4.968750075433821, "ce": 5.637393951416016, "genuineness": 4.519899368286133, "identity": 0.49170348048210144, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/fe0beff20f08743f5c48f3b1723f6b6b614cd8de971f1fca5debc15a9a6596e2.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": "fe0fcb751543fa8f376fbec3185add18484b4679606f08fb437095e977836ee7", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e5cd7b192ab5c5575eb4e3c5d36b6b37b19860306b5b1319ffb4c4a1148e1431", "generation_seconds_batch": 23.808462685905397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2200769186019897, "target_z": 2.625000177491343, "ce": 6.24500846862793, "genuineness": 4.457139015197754, "identity": 0.29929399490356445, "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_Awe/fe0fcb751543fa8f376fbec3185add18484b4679606f08fb437095e977836ee7.mp3" }, { "id": "emo_Awe-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Awe-nl-1", "key": "ff040f9ed3717dcc6e1a0938a7425aca11eb552cfc3207d7e9e826096b1cd9e9", "bucket": "emo_Awe", "phase": "grid", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Het stond naast het oude raam.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e61af6cde78d76803e81f5ec5a0bd961262424050fc52a95622412c56b6f276e", "generation_seconds_batch": 24.646020950051025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4854767322540283, "target_z": 0.875, "ce": 6.1020402908325195, "genuineness": 4.400654315948486, "identity": 0.5867605209350586, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Awe/ff040f9ed3717dcc6e1a0938a7425aca11eb552cfc3207d7e9e826096b1cd9e9.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": "ff129d28029998feeeaa4470d125f6ad189e899d0bfdd8746c384521a2d81a00", "bucket": "emo_Awe", "phase": "heldout", "candidate": "manual-51b69a70d1d3", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Establish it from the first phrase. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Sustain it through the thought. Let the local direction carry the intended delivery beside each sentence.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Quiet astonishment at something vast and beautiful; open resonance, reverent breath and spacious emphasis. Keep it audible in the final sentence. Let the local direction carry the intended delivery beside each sentence.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "14981067a0ddf1a78af02da4764fd42c4d126eedf946ec0dcd97a5a674d9fb35", "generation_seconds_batch": 23.27120200707577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6986419558525085, "target_z": 1.382812529951664, "ce": 6.1020402908325195, "genuineness": 4.65797233581543, "identity": 0.48834654688835144, "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_Awe/ff129d28029998feeeaa4470d125f6ad189e899d0bfdd8746c384521a2d81a00.mp3" }, { "key": "original-emo_Awe-de-0-seed1701-scale0.0", "bucket": "emo_Awe", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "f3bacab6394181ac9cf3f6dc5fb2e45a46609b1685ad4d3c13004d340d521f13", "task_id": "emo_Awe-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.02430199831724167, "target_z": -0.2236328090333722, "ce": 6.3641486167907715, "genuineness": 4.469690799713135, "identity": 0.599947988986969, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/de/2af344a472755eb548b00499.mp3" }, { "key": "original-emo_Awe-de-0-seed1701-scale0.5", "bucket": "emo_Awe", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "1341b577d60da093b9e2f86e51e10c0d6e8cb7e1ab95e7602c99ce8ee25ef521", "task_id": "emo_Awe-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.06160590797662735, "target_z": -0.13476562694131156, "ce": 6.229123115539551, "genuineness": 4.413206577301025, "identity": 0.4721446633338928, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/de/bb7a18bae8dcd03c30be9fa2.mp3" }, { "key": "original-emo_Awe-de-0-seed1701-scale0.75", "bucket": "emo_Awe", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "aa7b420945df8d6ad7fff1cc7a4f752117f609f3cba08a5ddc3749cb43d3093d", "task_id": "emo_Awe-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.052177444100379944, "target_z": -0.1572265706812416, "ce": 6.1894097328186035, "genuineness": 4.394378662109375, "identity": 0.6067169904708862, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/de/e14ff2982e0c526fef0cd604.mp3" }, { "key": "original-emo_Awe-de-0-seed1701-scale1.0", "bucket": "emo_Awe", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "b7048c7dd17e13acb6ce0e1e1941556c0a51c72ca7f8fa4504b33c39233c29a1", "task_id": "emo_Awe-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.06488537788391113, "target_z": -0.12695311473878174, "ce": 6.268836498260498, "genuineness": 4.381826400756836, "identity": 0.33583879470825195, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/de/b1495e29f9071e158dd678a2.mp3" }, { "key": "original-emo_Awe-de-0-seed1702-scale0.0", "bucket": "emo_Awe", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "23206b1af89bce757fe41ae87b4041320ce0d454335689682129ace4a660a7d6", "task_id": "emo_Awe-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.04438871890306473, "target_z": -0.17578124944533954, "ce": 6.078212261199951, "genuineness": 4.406930446624756, "identity": 0.6484034061431885, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/de/1dc52a04dde2bfd3105f159f.mp3" }, { "key": "original-emo_Awe-de-0-seed1702-scale0.5", "bucket": "emo_Awe", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "bcaa8039f7dd6c17fb422fc57b1f72f7652d873b8a6667e08f800b315f99b8a7", "task_id": "emo_Awe-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.03700992465019226, "target_z": -0.19335937084004665, "ce": 6.284721851348877, "genuineness": 4.494794845581055, "identity": 0.5360069274902344, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/de/ee7ff66f751fb20a3444cb0a.mp3" }, { "key": "original-emo_Awe-de-0-seed1702-scale0.75", "bucket": "emo_Awe", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "7ff3849e667118fe4cdb6ff765bd4b16e5f0d2e469abfddedadf9cfff151ba0d", "task_id": "emo_Awe-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.0390595868229866, "target_z": -0.188476566243958, "ce": 6.09409761428833, "genuineness": 4.3504462242126465, "identity": 0.661853015422821, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/de/a0eb1a2beed76c08607ed3f2.mp3" }, { "key": "original-emo_Awe-de-0-seed1702-scale1.0", "bucket": "emo_Awe", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "afb1c7465ed62dc6b1ba1df3ce3ac7a98169fb1d8eee1429c647186ad90abbc4", "task_id": "emo_Awe-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.083332359790802, "target_z": -0.08300782012658114, "ce": 6.070269584655762, "genuineness": 4.632867813110352, "identity": 0.698826014995575, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/de/1d81f95044816c0680ba62c4.mp3" }, { "key": "original-emo_Awe-de-1-seed1701-scale0.0", "bucket": "emo_Awe", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "8b54f98bc0985b30d5cacbbc8fccc7d8b9dd7e47b5ac3071640812335a528b16", "task_id": "emo_Awe-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.7445544600486755, "target_z": 1.4921875232957387, "ce": 6.38003396987915, "genuineness": 4.507347106933594, "identity": 0.5974147319793701, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/de/1654af5a83af3849fd263e64.mp3" }, { "key": "original-emo_Awe-de-1-seed1701-scale0.5", "bucket": "emo_Awe", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "15f715ff44a45635175f9907e4917d2405e416ad947073548d1e28a9f69539bc", "task_id": "emo_Awe-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.724877655506134, "target_z": 1.4453124855788284, "ce": 6.403861999511719, "genuineness": 4.268857479095459, "identity": 0.2554647922515869, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/de/ffddc2399e4dd6ef010e51aa.mp3" }, { "key": "original-emo_Awe-de-1-seed1701-scale0.75", "bucket": "emo_Awe", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "970e1109a8dae4130872ba0c6f92b4378728c004c3826afcc986f75e713a7570", "task_id": "emo_Awe-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.2706717848777771, "target_z": 0.3632812405707724, "ce": 6.356205940246582, "genuineness": 4.143336772918701, "identity": 0.313959538936615, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/de/42704da8a676b90e35bd61fb.mp3" }, { "key": "original-emo_Awe-de-1-seed1701-scale1.0", "bucket": "emo_Awe", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "64e6cd3f02debbb8ee6a7a64a5470f5ef644b1e7e5715203ff6070b3ac1549fb", "task_id": "emo_Awe-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.5445070862770081, "target_z": 1.0156249711576568, "ce": 6.324435234069824, "genuineness": 4.2751336097717285, "identity": 0.45968112349510193, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/de/fe8faef360fc8835ab43ecee.mp3" }, { "key": "original-emo_Awe-de-1-seed1702-scale0.0", "bucket": "emo_Awe", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "5823b71442eecf8939feb39ce4eae999e765247e3dbfd312f360b9146a67404a", "task_id": "emo_Awe-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.3133048415184021, "target_z": 0.4648437749597201, "ce": 6.340320587158203, "genuineness": 4.306513786315918, "identity": 0.5935660600662231, "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/audio/emo_Awe/de/c020dfe73a61ea51fed93cf7.mp3" }, { "key": "original-emo_Awe-de-1-seed1702-scale0.5", "bucket": "emo_Awe", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "b9176ae8552e91e1e9a220a05e5c014f4820b38eaead2a9893c9fb89187e74b7", "task_id": "emo_Awe-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.8396589756011963, "target_z": 1.7187501109320893, "ce": 6.38797664642334, "genuineness": 4.306513786315918, "identity": 0.42576485872268677, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/de/4b1fad4632bc3e38e0e1451a.mp3" }, { "key": "original-emo_Awe-de-1-seed1702-scale0.75", "bucket": "emo_Awe", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "108a2bcd837fe1bdd42693c8543c58f43d3a8a22b94482f2c50ac82cf316d5de", "task_id": "emo_Awe-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.45924100279808044, "target_z": 0.8124999733762985, "ce": 6.443574905395508, "genuineness": 4.21237325668335, "identity": 0.45723026990890503, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/de/bd97ad28327907deed60f15d.mp3" }, { "key": "original-emo_Awe-de-1-seed1702-scale1.0", "bucket": "emo_Awe", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "76beb6031e8345003f9e9d2368a3482b366f4c350986e2d1993d7fcc08249588", "task_id": "emo_Awe-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.8003053665161133, "target_z": 1.6250000354982685, "ce": 6.38003396987915, "genuineness": 4.381826400756836, "identity": 0.45287829637527466, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/de/84bc23c3c5a0e4eb45fe8358.mp3" }, { "key": "original-emo_Awe-en-0-seed1701-scale0.0", "bucket": "emo_Awe", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "5618d48fbe722bcfda0f8b0c4d11db7cb0883ed8666558fa3c7d9f8b454e3f32", "task_id": "emo_Awe-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.07267410308122635, "target_z": -0.10839843597468377, "ce": 6.165581703186035, "genuineness": 4.306513786315918, "identity": 0.4055059552192688, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/en/b26373c2a84c24fb3423330d.mp3" }, { "key": "original-emo_Awe-en-0-seed1701-scale0.5", "bucket": "emo_Awe", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "97ab7c7db062c58a9ee8de30917109a70c933d6612d20d7b55b53575434c6789", "task_id": "emo_Awe-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.10177935659885406, "target_z": -0.03906249001611196, "ce": 6.125868320465088, "genuineness": 4.105680465698242, "identity": 0.39020317792892456, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/en/f45a889cf87e77e0ad404a06.mp3" }, { "key": "original-emo_Awe-en-0-seed1701-scale0.75", "bucket": "emo_Awe", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "6250ca89aaebd1ee0b910762118d52e71353144c83f7b32d0196174052d0c4f7", "task_id": "emo_Awe-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.09235089272260666, "target_z": -0.06152343375604198, "ce": 6.340320587158203, "genuineness": 4.306513786315918, "identity": 0.280155211687088, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/en/68a78232732e7090887c502d.mp3" }, { "key": "original-emo_Awe-en-0-seed1701-scale1.0", "bucket": "emo_Awe", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "e517545b679759734af34b95a78d99ced9e8a68a09eeefd4313f32c0f7fe771e", "task_id": "emo_Awe-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.05053771287202835, "target_z": -0.16113281790793935, "ce": 6.221180438995361, "genuineness": 3.8295347690582275, "identity": 0.35540902614593506, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/en/7fc045b4b1ba79460d49f6d7.mp3" }, { "key": "original-emo_Awe-en-0-seed1702-scale0.0", "bucket": "emo_Awe", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "91e6a4044827044780ed0aad0441b46425195e57e98e67b44b5ed52e0d0dc262", "task_id": "emo_Awe-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.072264164686203, "target_z": -0.10937501109320893, "ce": 6.1894097328186035, "genuineness": 4.168440818786621, "identity": 0.3571431636810303, "hypothesis": "The 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_Awe/en/ba112b9a93b5bb829911569f.mp3" }, { "key": "original-emo_Awe-en-0-seed1702-scale0.5", "bucket": "emo_Awe", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "c2137be7f5c8ea65a17c16bb1ebae69b8a4b2d9de0640c5a3233d2df6689ca70", "task_id": "emo_Awe-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.0714443027973175, "target_z": -0.11132812583199067, "ce": 6.078212261199951, "genuineness": 3.9676074981689453, "identity": 0.22918400168418884, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/en/4823ab667522afe7873214a2.mp3" }, { "key": "original-emo_Awe-en-0-seed1702-scale0.75", "bucket": "emo_Awe", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "d59efba95520508376d2b88afc711a21715f081e15e4732772098258a9bca017", "task_id": "emo_Awe-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.21000169217586517, "target_z": 0.21875000443728357, "ce": 6.284721851348877, "genuineness": 4.055472373962402, "identity": 0.4483690857887268, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/en/14ae261aa237af539a08febf.mp3" }, { "key": "original-emo_Awe-en-0-seed1702-scale1.0", "bucket": "emo_Awe", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 1.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "ce5aaa8e673e7c1116fb7be762254b6c45d257cbe6c299b8e3d7e76be19bc964", "task_id": "emo_Awe-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.15384085476398468, "target_z": 0.08496093486536288, "ce": 6.181467056274414, "genuineness": 4.017816066741943, "identity": 0.28640130162239075, "hypothesis": "The 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_Awe/en/65c73e021c4c51288c26e4f4.mp3" }, { "key": "original-emo_Awe-en-1-seed1701-scale0.0", "bucket": "emo_Awe", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "8066a1c0bf96a8bdb821215a7bcb599404e1a0725755f728bd56a7eb8a65194b", "task_id": "emo_Awe-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1676054000854492, "target_z": 2.499999982250866, "ce": 6.324435234069824, "genuineness": 4.68307638168335, "identity": 0.4112547039985657, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/en/e699fef02c6d6302d2b5b60b.mp3" }, { "key": "original-emo_Awe-en-1-seed1701-scale0.5", "bucket": "emo_Awe", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "b41ae6ca9daccb7e0ccfd24f526021a4f99fbcc156fbded89d3ee90a58919ae1", "task_id": "emo_Awe-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.5117124319076538, "target_z": 0.9374999556271643, "ce": 6.229123115539551, "genuineness": 4.444586753845215, "identity": 0.35625159740448, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/en/99842393a035ede581ec7884.mp3" }, { "key": "original-emo_Awe-en-1-seed1701-scale0.75", "bucket": "emo_Awe", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "2c5d0d52840a11f923b7730e008aa9f4693894250a4dd2ad3fc5370c69b6a91f", "task_id": "emo_Awe-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1216928958892822, "target_z": 2.390624988906791, "ce": 6.348263263702393, "genuineness": 4.444586753845215, "identity": 0.46343424916267395, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/en/37f6b9e90493383d189a2231.mp3" }, { "key": "original-emo_Awe-en-1-seed1701-scale1.0", "bucket": "emo_Awe", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "ab26ef8742785012a5bb506f230c08d2520a029ea5c75059e859e48e45178f57", "task_id": "emo_Awe-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0561035871505737, "target_z": 2.234374957845806, "ce": 6.38797664642334, "genuineness": 4.419482707977295, "identity": 0.5419123768806458, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/en/2971ac1dfb34be3944bdb6bb.mp3" }, { "key": "original-emo_Awe-en-1-seed1702-scale0.0", "bucket": "emo_Awe", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "df323af59bcf96db749c7fbb42d63ae5d275b9acbc4554cb38fede514a16402c", "task_id": "emo_Awe-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2659894227981567, "target_z": 2.734375170835418, "ce": 6.316492557525635, "genuineness": 4.457139015197754, "identity": 0.39078810811042786, "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/audio/emo_Awe/en/ca1c7d9b52ed69565e6f7b14.mp3" }, { "key": "original-emo_Awe-en-1-seed1702-scale0.5", "bucket": "emo_Awe", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "b1a9d77fdb19013a8d57ba1662551624a87a1bb307bdd5ab9dc122a6be5e4443", "task_id": "emo_Awe-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5349054336547852, "target_z": 3.374999929003463, "ce": 6.332377910614014, "genuineness": 4.381826400756836, "identity": 0.35721611976623535, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/en/08fcd30f2bf7971f00f54c7f.mp3" }, { "key": "original-emo_Awe-en-1-seed1702-scale0.75", "bucket": "emo_Awe", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "a8a36e2f2a580eaf8a8385c05ffe79bc1ca4a1b8942824dd353cf79899403021", "task_id": "emo_Awe-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.9642786383628845, "target_z": 2.015625113150731, "ce": 6.38797664642334, "genuineness": 4.457139015197754, "identity": 0.46727824211120605, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/en/59bc183b70e374105d63d216.mp3" }, { "key": "original-emo_Awe-en-1-seed1702-scale1.0", "bucket": "emo_Awe", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "b498e72acdd040de68435f2f5a7e9f81a7a8adf6888e244da1a576acdbcb312b", "task_id": "emo_Awe-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.8331000208854675, "target_z": 1.7031250510287612, "ce": 6.4515180587768555, "genuineness": 4.507347106933594, "identity": 0.24160194396972656, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/en/a30a3c90aa8c0be4e1d79071.mp3" }, { "key": "original-emo_Awe-es-0-seed1701-scale0.0", "bucket": "emo_Awe", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "2f14edb27d044edfffefe25eadece3287d08239ebf355fb0962a7c48cbc4470a", "task_id": "emo_Awe-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.10177935659885406, "target_z": -0.03906249001611196, "ce": 6.117925643920898, "genuineness": 4.086852550506592, "identity": 0.6352806091308594, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/es/68c182942c9d856b4b5882c8.mp3" }, { "key": "original-emo_Awe-es-0-seed1701-scale0.5", "bucket": "emo_Awe", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "52cdbcab94499a5a93356a618fa2367776b2d37eb9b7ecec002d633553cd832b", "task_id": "emo_Awe-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.2255791425704956, "target_z": 0.2558593619654795, "ce": 6.125868320465088, "genuineness": 4.400654315948486, "identity": 0.5914168357849121, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/es/3c8dafac004c0b5ab55a2cb5.mp3" }, { "key": "original-emo_Awe-es-0-seed1701-scale0.75", "bucket": "emo_Awe", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "1fc3a5c1238cb5c7b489fe7033d687b13a6aa47aa06eafab24c55f2d739938f6", "task_id": "emo_Awe-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.2755909860134125, "target_z": 0.375, "ce": 5.903473377227783, "genuineness": 4.118232727050781, "identity": 0.5004051923751831, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/es/684d26e109b56ef907f1eb6a.mp3" }, { "key": "original-emo_Awe-es-0-seed1701-scale1.0", "bucket": "emo_Awe", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "bd123f33d9b21965ce46fa07c7cd1571e1b9c12183329fe950b59e7e9973a7f6", "task_id": "emo_Awe-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.10054954886436462, "target_z": -0.04199219762255316, "ce": 6.09409761428833, "genuineness": 4.65797233581543, "identity": 0.5183166861534119, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/es/e1257609a59df87b5a252493.mp3" }, { "key": "original-emo_Awe-es-0-seed1702-scale0.0", "bucket": "emo_Awe", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "8bc115b8f53082b4ec5c6c64c3fffaee49bdd650a7af4bfa24219a5df174d334", "task_id": "emo_Awe-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.2534545958042145, "target_z": 0.3222656180667444, "ce": 6.125868320465088, "genuineness": 4.15588903427124, "identity": 0.4935712516307831, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/es/5e97bb0f8f358fdb25c5fca2.mp3" }, { "key": "original-emo_Awe-es-0-seed1702-scale0.5", "bucket": "emo_Awe", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "52932275148f737425ba16252fb4ee71af70cc6fc72948abebe4b3ae26c8e199", "task_id": "emo_Awe-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.14154286682605743, "target_z": 0.055664071790562486, "ce": 5.982900142669678, "genuineness": 4.143336772918701, "identity": 0.43643462657928467, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/es/2b2e503f0b30ee4c7ea87396.mp3" }, { "key": "original-emo_Awe-es-0-seed1702-scale0.75", "bucket": "emo_Awe", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "1750429fed9d8dd2780bbc3faa921eb19ccd7635a1070b96e39e1d5042fb2138", "task_id": "emo_Awe-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.5084329843521118, "target_z": 0.9296874966720373, "ce": 6.046441555023193, "genuineness": 4.118232727050781, "identity": 0.26656728982925415, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/es/baa98efe31f0736fa3f7f101.mp3" }, { "key": "original-emo_Awe-es-0-seed1702-scale1.0", "bucket": "emo_Awe", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 1.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "b7da0621c4ebb2eeadc0c657cc265c1a5b42b698b796e2a35e310df19addd68b", "task_id": "emo_Awe-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.10054954886436462, "target_z": -0.04199219762255316, "ce": 6.046441555023193, "genuineness": 4.168440818786621, "identity": 0.6216202974319458, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/es/f4b91e1c11ae6815cfd15338.mp3" }, { "key": "original-emo_Awe-es-1-seed1701-scale0.0", "bucket": "emo_Awe", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "838ee18b4265a431c74a30fbff5e912056875382703fec9767849239cae55c2b", "task_id": "emo_Awe-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.810143768787384, "target_z": 1.6484375543567238, "ce": 6.09409761428833, "genuineness": 4.557555198669434, "identity": 0.5720688700675964, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/es/3ad4a8fd854e33a0aedf5a09.mp3" }, { "key": "original-emo_Awe-es-1-seed1701-scale0.5", "bucket": "emo_Awe", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "dc9c693258839bf29d6cabe9f107f849708ac4aa9414ea2dd5b0ccc767dd3209", "task_id": "emo_Awe-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.41496822237968445, "target_z": 0.7070312095097874, "ce": 6.09409761428833, "genuineness": 4.532451152801514, "identity": 0.6651809811592102, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/es/553897b3924afd23edbcaad1.mp3" }, { "key": "original-emo_Awe-es-1-seed1701-scale0.75", "bucket": "emo_Awe", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "3116cf6b5de3033fdd4b984770878cda4a773d1c07f4775e1105119cddd23919", "task_id": "emo_Awe-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 1.0757803916931152, "target_z": 2.2812499955627166, "ce": 6.125868320465088, "genuineness": 4.344170093536377, "identity": 0.6006138324737549, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/es/41bc5b0971927ac06de691ad.mp3" }, { "key": "original-emo_Awe-es-1-seed1701-scale1.0", "bucket": "emo_Awe", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "a5658d7fe32dd832b2006e62cc592f02256bb147b261c9e2e50f30902cb9fba7", "task_id": "emo_Awe-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.813423216342926, "target_z": 1.6562500133118507, "ce": 6.229123115539551, "genuineness": 4.20609712600708, "identity": 0.49144914746284485, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/es/d585b296050d0899372a8281.mp3" }, { "key": "original-emo_Awe-es-1-seed1702-scale0.0", "bucket": "emo_Awe", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "1e2cba9f90c9fb1a3161982d23744abed8ac91720f30367fa75e6dfedc4de392", "task_id": "emo_Awe-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.138673335313797, "target_z": 0.04882813470655782, "ce": 6.181467056274414, "genuineness": 4.909013748168945, "identity": 0.5734210014343262, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/es/4f142e63688c0497d2d21e26.mp3" }, { "key": "original-emo_Awe-es-1-seed1702-scale0.5", "bucket": "emo_Awe", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "d3f7a6dda3e16895b8b6e61f65e790b831045e78823d7956f02150b8262645c0", "task_id": "emo_Awe-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.590419590473175, "target_z": 1.1249999645017315, "ce": 6.149696350097656, "genuineness": 4.168440818786621, "identity": 0.7062333822250366, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/es/052fd1f621b43b361a9e2d30.mp3" }, { "key": "original-emo_Awe-es-1-seed1702-scale0.75", "bucket": "emo_Awe", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "73f6d7111f14e871860abb0dfc69dffcf2266a133ef549eefbd6bd04238ac502", "task_id": "emo_Awe-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.3575775921344757, "target_z": 0.570312467829694, "ce": 6.133810997009277, "genuineness": 4.406930446624756, "identity": 0.6984769105911255, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/es/71987f3fea583c385f821091.mp3" }, { "key": "original-emo_Awe-es-1-seed1702-scale1.0", "bucket": "emo_Awe", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "021fdcc7c4b2f5e261bb34273b729aef7d5352280149f2fda7b10811d0ef1d97", "task_id": "emo_Awe-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.7543928623199463, "target_z": 1.515625042154194, "ce": 6.173524379730225, "genuineness": 4.337893962860107, "identity": 0.6303586959838867, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/es/f775aaa57da1e2edd444950f.mp3" }, { "key": "original-emo_Awe-fr-0-seed1701-scale0.0", "bucket": "emo_Awe", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "18fb2021d805200071473c76f491170dd785c6a8c7723f3ee0dcdec0be8819bc", "task_id": "emo_Awe-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.07636350393295288, "target_z": -0.09960936640276308, "ce": 5.967014789581299, "genuineness": 4.381826400756836, "identity": 0.414029598236084, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/fr/fee8b7d646f16a4f385bb0c9.mp3" }, { "key": "original-emo_Awe-fr-0-seed1701-scale0.5", "bucket": "emo_Awe", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "32006ba81db42e379be1fd7f410686ddac4c1d3b1e834cc7c489cf91e67db918", "task_id": "emo_Awe-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.10833828151226044, "target_z": -0.023437501109320896, "ce": 6.157639026641846, "genuineness": 4.331617832183838, "identity": 0.7596856355667114, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/fr/59a2499fafde6b2902aedd79.mp3" }, { "key": "original-emo_Awe-fr-0-seed1701-scale0.75", "bucket": "emo_Awe", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "a3c5771d62a5104d0c47606f8d387630cd57eaeb8e3919625ffb4c1603ca9641", "task_id": "emo_Awe-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.15548059344291687, "target_z": 0.08886719984119494, "ce": 6.23706579208374, "genuineness": 4.457139015197754, "identity": 0.5347900986671448, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/fr/1e0443a0556e44794c527f02.mp3" }, { "key": "original-emo_Awe-fr-0-seed1701-scale1.0", "bucket": "emo_Awe", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "3a813bab232fb3faa7a2d362210d5af4ab8d866d00d279a49bd35895e9abc06d", "task_id": "emo_Awe-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.08292242884635925, "target_z": -0.08398437749597201, "ce": 6.078212261199951, "genuineness": 4.268857479095459, "identity": 0.8289244771003723, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/fr/18b7b1ebe2250de2277f365b.mp3" }, { "key": "original-emo_Awe-fr-0-seed1702-scale0.0", "bucket": "emo_Awe", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "27cd20ddb415336a20e77d056d54815c069b6a3baf84f2a8b48f54523d25e7d5", "task_id": "emo_Awe-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.05258738249540329, "target_z": -0.15624999556271643, "ce": 6.133810997009277, "genuineness": 4.632867813110352, "identity": 0.580538272857666, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/fr/984a50e669d32c70accae082.mp3" }, { "key": "original-emo_Awe-fr-0-seed1702-scale0.5", "bucket": "emo_Awe", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "ba6a2dbe44cfedcd8ab653c3348e445db46db19868d8800c88ebfb62bdf44a6f", "task_id": "emo_Awe-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.12309587001800537, "target_z": 0.011718741680093295, "ce": 6.157639026641846, "genuineness": 4.770940780639648, "identity": 0.7294873595237732, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/fr/b34e9167243ba2af2dc6d424.mp3" }, { "key": "original-emo_Awe-fr-0-seed1702-scale0.75", "bucket": "emo_Awe", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "e440b3e58bd286bbabc49fdab27316cd122ac61b85fe33ac1c3a9716af732c76", "task_id": "emo_Awe-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.09768001735210419, "target_z": -0.04882813470655782, "ce": 6.205295085906982, "genuineness": 4.632867813110352, "identity": 0.5766433477401733, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/fr/12559e8c435477b2555228b0.mp3" }, { "key": "original-emo_Awe-fr-0-seed1702-scale1.0", "bucket": "emo_Awe", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "efa544f2cfc30e95b49c4562de9e46bf5dcec5786e0ecf633ac61779f8e6f9d7", "task_id": "emo_Awe-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.10054954886436462, "target_z": -0.04199219762255316, "ce": 6.2767791748046875, "genuineness": 4.256305694580078, "identity": 0.6946443319320679, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/fr/91dabde374e983a1af4ceed5.mp3" }, { "key": "original-emo_Awe-fr-1-seed1701-scale0.0", "bucket": "emo_Awe", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "82c6d46a6b13b995ac025a7af7836c2300c4250788246a5da211b0bf8e690704", "task_id": "emo_Awe-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.6232143044471741, "target_z": 1.2031251220252983, "ce": 6.173524379730225, "genuineness": 4.482243061065674, "identity": 0.6875790357589722, "hypothesis": "J'ai trouvé la 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_Awe/fr/843471203ce8eed36090e95c.mp3" }, { "key": "original-emo_Awe-fr-1-seed1701-scale0.5", "bucket": "emo_Awe", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "9b88093cff070afba51f0c437daff232ac4c57a0062a520b42f14bbab25dffaf", "task_id": "emo_Awe-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.5543454885482788, "target_z": 1.039062490016112, "ce": 6.205295085906982, "genuineness": 4.369274139404297, "identity": 0.6204805374145508, "hypothesis": "J'ai trouvé la 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_Awe/fr/61bd7946360e8647efd040c8.mp3" }, { "key": "original-emo_Awe-fr-1-seed1701-scale0.75", "bucket": "emo_Awe", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "c41f32d896e5c13a34f34071f5e0e6eba5f6c99a6a6bd3b4b2fe5d69ec51bd79", "task_id": "emo_Awe-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.5773017406463623, "target_z": 1.0937499866881493, "ce": 6.181467056274414, "genuineness": 4.381826400756836, "identity": 0.8872002363204956, "hypothesis": "J'ai trouvé la 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_Awe/fr/86835d36714eb1323646fe91.mp3" }, { "key": "original-emo_Awe-fr-1-seed1701-scale1.0", "bucket": "emo_Awe", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "c00174cd7d1da41901bc5991fe3d6e5c62e288a29326d83ee354a1455ec2b3ed", "task_id": "emo_Awe-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.678965151309967, "target_z": 1.3359374922347538, "ce": 6.078212261199951, "genuineness": 4.419482707977295, "identity": 0.7205519676208496, "hypothesis": "J'ai trouvé la 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_Awe/fr/1070a5eb34122ecb2e95039a.mp3" }, { "key": "original-emo_Awe-fr-1-seed1702-scale0.0", "bucket": "emo_Awe", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "b8c565c98e59b13dec0a29e6f2be42610738f46241b9bb3fcd85af463642f7b9", "task_id": "emo_Awe-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.43628475069999695, "target_z": 0.7578124767042612, "ce": 6.252951145172119, "genuineness": 4.570107460021973, "identity": 0.6550630331039429, "hypothesis": "J'ai trouvé la 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_Awe/fr/43011516647a08adcf2f5f9f.mp3" }, { "key": "original-emo_Awe-fr-1-seed1702-scale0.5", "bucket": "emo_Awe", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "dce1eb282960100b7bf600f3d484a626166cf5643e94913c0699fcb6bb6f84c5", "task_id": "emo_Awe-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.7478339672088623, "target_z": 1.50000012424394, "ce": 6.221180438995361, "genuineness": 4.419482707977295, "identity": 0.7612985372543335, "hypothesis": "J'ai trouvé la 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_Awe/fr/6f6f825b7940d516caa8974f.mp3" }, { "key": "original-emo_Awe-fr-1-seed1702-scale0.75", "bucket": "emo_Awe", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "8e87d6f3949bbbc9362862a309d5a9e24a7248d9a98bb8aa1c18150d265ebd85", "task_id": "emo_Awe-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.5199111104011536, "target_z": 0.957031245008056, "ce": 6.1020402908325195, "genuineness": 4.432034492492676, "identity": 0.7312532663345337, "hypothesis": "J'ai trouvé la 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_Awe/fr/7d6f61b78c6583bf3dba6a8e.mp3" }, { "key": "original-emo_Awe-fr-1-seed1702-scale1.0", "bucket": "emo_Awe", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "c1112ec9486e9972f081dcd1550f1af7dc8a1d0a0b673d97fb5afa70eb17d7f7", "task_id": "emo_Awe-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.6330526471138, "target_z": 1.2265624988906791, "ce": 6.2767791748046875, "genuineness": 4.507347106933594, "identity": 0.799504816532135, "hypothesis": "J'ai trouvé la 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_Awe/fr/d853e10708e1f5cc268cc958.mp3" }, { "key": "original-emo_Awe-nl-0-seed1701-scale0.0", "bucket": "emo_Awe", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "cb194bbd7bb6dca2ca89ddcfa74c3cbfa97e1d099879bf1d2c74eb9060e378eb", "task_id": "emo_Awe-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.2723115086555481, "target_z": 0.36718747004833585, "ce": 6.23706579208374, "genuineness": 4.331617832183838, "identity": 0.6134315729141235, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/nl/acfb84921d5283d374ad7bea.mp3" }, { "key": "original-emo_Awe-nl-0-seed1701-scale0.5", "bucket": "emo_Awe", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "535610dfb5aa801acc5357e7ddafeac3f93374c54a4db2560ed631d9a8e99b1f", "task_id": "emo_Awe-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.39365172386169434, "target_z": 0.6562500133118507, "ce": 6.165581703186035, "genuineness": 4.231201171875, "identity": 0.6066974401473999, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/nl/ea68bd7293fdc124b9b86303.mp3" }, { "key": "original-emo_Awe-nl-0-seed1701-scale0.75", "bucket": "emo_Awe", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "d9d29d10e395a88b18a407489d23d8fea131491cc8739ea8af47057feab42eec", "task_id": "emo_Awe-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.15302099287509918, "target_z": 0.08300782012658114, "ce": 6.125868320465088, "genuineness": 3.986435890197754, "identity": 0.6965957880020142, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/nl/331af9c99fb648c017560f6a.mp3" }, { "key": "original-emo_Awe-nl-0-seed1701-scale1.0", "bucket": "emo_Awe", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "27e8ec950a695cd9176d75baeef22b9bd332708bbf5beb3a4ba59ad6be8dc98c", "task_id": "emo_Awe-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.055866844952106476, "target_z": -0.14843750110932089, "ce": 6.078212261199951, "genuineness": 4.124508857727051, "identity": 0.6893452405929565, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/nl/dbeef7e6bab50554525ac0d8.mp3" }, { "key": "original-emo_Awe-nl-0-seed1702-scale0.0", "bucket": "emo_Awe", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "922f5d56b7289e7388222b964a53eee0cd9459cc9e66e64b37ad24f722166554", "task_id": "emo_Awe-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.055866844952106476, "target_z": -0.14843750110932089, "ce": 6.09409761428833, "genuineness": 4.13078498840332, "identity": 0.47552502155303955, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/nl/174db9a812e075087e077c8d.mp3" }, { "key": "original-emo_Awe-nl-0-seed1702-scale0.5", "bucket": "emo_Awe", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "8b9f46297ae71af0dbb3ab325b141e823ae744d82f54f3a706aa8e5b48b1d016", "task_id": "emo_Awe-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.043158918619155884, "target_z": -0.17871093930264645, "ce": 6.125868320465088, "genuineness": 4.356721878051758, "identity": 0.4882906675338745, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/nl/eef4e5f66f3309ecb363fc73.mp3" }, { "key": "original-emo_Awe-nl-0-seed1702-scale0.75", "bucket": "emo_Awe", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "513dfa9b74f5d2cb1f5b2386d0122721d1e3c779e9bf0159f74b4c95510b9558", "task_id": "emo_Awe-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.08005289733409882, "target_z": -0.09082031457997668, "ce": 5.998785495758057, "genuineness": 4.381826400756836, "identity": 0.37240439653396606, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/nl/fe59800ada0200e0684f23a5.mp3" }, { "key": "original-emo_Awe-nl-0-seed1702-scale1.0", "bucket": "emo_Awe", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "e9de6a0b22c3072c6eff542c143259270b7d0aa01ca3da3982e7997774147100", "task_id": "emo_Awe-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.21082155406475067, "target_z": 0.2207031191760653, "ce": 6.022613525390625, "genuineness": 4.306513786315918, "identity": 0.3517378270626068, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/nl/a26fc630ea860c65e07ea38f.mp3" }, { "key": "original-emo_Awe-nl-1-seed1701-scale0.0", "bucket": "emo_Awe", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "091a29dd4b6488108f23910737dfc929c5bb6b043573c59e8eb70a13c8f59b11", "task_id": "emo_Awe-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.046848319470882416, "target_z": -0.16992186973072576, "ce": 6.1020402908325195, "genuineness": 4.356721878051758, "identity": 0.6429229378700256, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/nl/72212b5fe68d916164cdf457.mp3" }, { "key": "original-emo_Awe-nl-1-seed1701-scale0.5", "bucket": "emo_Awe", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "f6c2d706d4d5b48a9cce19d7545ebb56d903697b9d186de736bd275e3a07a5bd", "task_id": "emo_Awe-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.05955624207854271, "target_z": -0.13964844041196733, "ce": 6.165581703186035, "genuineness": 4.18726921081543, "identity": 0.6562211513519287, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/nl/6f0b06a4ff95338c8d79112f.mp3" }, { "key": "original-emo_Awe-nl-1-seed1701-scale0.75", "bucket": "emo_Awe", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "31c3393bd980d920ef79e734d5092a51a198b32ac211234ad449c7fd1426c1cf", "task_id": "emo_Awe-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.042748987674713135, "target_z": -0.17968749667203732, "ce": 6.038498878479004, "genuineness": 4.444586753845215, "identity": 0.49656349420547485, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/nl/d1b73881537d91e09d7bffb5.mp3" }, { "key": "original-emo_Awe-nl-1-seed1701-scale1.0", "bucket": "emo_Awe", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "f6ef22c7709cb54833b3d4c2f9c66c8bdba100b71f9924b346553b2b86875d3f", "task_id": "emo_Awe-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.05873637646436691, "target_z": -0.14160156402531623, "ce": 6.300607204437256, "genuineness": 4.369274139404297, "identity": 0.706683874130249, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/nl/9c2d292f355f5fa040c21881.mp3" }, { "key": "original-emo_Awe-nl-1-seed1702-scale0.0", "bucket": "emo_Awe", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "3dd1acc9c4fee23dfded03cb1ab851315db8712e4ff22720d924622b421ca0dc", "task_id": "emo_Awe-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.06447543948888779, "target_z": -0.1279296898573069, "ce": 6.252951145172119, "genuineness": 4.344170093536377, "identity": 0.6630468368530273, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/nl/739e6b712ada05f78177a119.mp3" }, { "key": "original-emo_Awe-nl-1-seed1702-scale0.5", "bucket": "emo_Awe", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "2ca2aabd844a9951e13a051bd4f98281ce42b03dd7f5ceee3280c6cfbae58053", "task_id": "emo_Awe-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.08046282827854156, "target_z": -0.08984375721058581, "ce": 6.109982967376709, "genuineness": 4.300237655639648, "identity": 0.71174556016922, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/nl/9b216f53d11afcdcc497c653.mp3" }, { "key": "original-emo_Awe-nl-1-seed1702-scale0.75", "bucket": "emo_Awe", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "a90626528c911925d4aa7cf96efd6a82a8fe7891643d2a14e5c801c352104e65", "task_id": "emo_Awe-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.047668181359767914, "target_z": -0.16796875499194402, "ce": 6.165581703186035, "genuineness": 4.331617832183838, "identity": 0.6957493424415588, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/nl/abe138e4e831ac9edfac72cf.mp3" }, { "key": "original-emo_Awe-nl-1-seed1702-scale1.0", "bucket": "emo_Awe", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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 Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "572540bd10c92d1b0dabd0b1f78f6ca14c996634068e3db808b6f56a472ddce5", "mp3_sha256": "74e5c091a1afa819916d6b3f3525b9b779f0305401bf1c2bd948e05a3e8ca2ab", "task_id": "emo_Awe-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Awe. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Awe. 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 Awe. 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 Awe. 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": 0.06775490939617157, "target_z": -0.12011717765477707, "ce": 6.117925643920898, "genuineness": 4.494794845581055, "identity": 0.5972245335578918, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Awe/nl/c3f05b414a6f92925348a810.mp3" } ], "source_standard_audio_unchanged": true }